{
  "schema_version": 1,
  "categories": [
    {
      "id": "assets",
      "label": "Visual assets",
      "description": "Visual-asset generation and editing methods.",
      "count": 52
    },
    {
      "id": "scenes",
      "label": "Spatial scenes",
      "description": "Spatial scene generation and editing methods.",
      "count": 49
    },
    {
      "id": "temporal",
      "label": "Temporal content & worlds",
      "description": "Video generation, time-varying 3D content, and action-conditioned worlds.",
      "count": 72
    },
    {
      "id": "xr",
      "label": "XR systems",
      "description": "XR authoring systems and generated-content presentation methods.",
      "count": 31
    },
    {
      "id": "resources",
      "label": "Datasets & benchmarks",
      "description": "Datasets, simulators, and evaluation benchmarks used in the review.",
      "count": 37
    }
  ],
  "entries": [
    {
      "id": "A1",
      "name": "3D-GAN",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Learned geometry and 3D-aware generation",
      "bibkey": "Wu2016ThreeDGAN",
      "title": "Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling",
      "year": 2016,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Jiajun Wu and Chengkai Zhang and Tianfan Xue and William T. Freeman and Joshua B. Tenenbaum",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper_files/paper/2016/hash/44f683a84163b3523afe57c2e008bc8c-Abstract.html",
      "doi": "",
      "arxiv": "1610.07584",
      "source": "manuscript/tables/catalogue-assets.tex:25",
      "project_url": "",
      "url": "https://proceedings.neurips.cc/paper_files/paper/2016/hash/44f683a84163b3523afe57c2e008bc8c-Abstract.html",
      "kind": "method",
      "input_tags": [
        "N"
      ],
      "inputs": [
        "Latent / random seed"
      ],
      "description": "GAN · Voxel grid · Voxel shapes",
      "fields": {
        "Input": "Latent / random seed",
        "Mechanism": "GAN",
        "Representation / state": "Voxel grid",
        "Output": "Voxel shapes",
        "Stage": "P"
      }
    },
    {
      "id": "A2",
      "name": "Latent-GMM",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Learned geometry and 3D-aware generation",
      "bibkey": "Achlioptas2018PointClouds",
      "title": "Learning Representations and Generative Models for 3D Point Clouds",
      "year": 2018,
      "venue": "Proceedings of the International Conference on Machine Learning",
      "authors": "Panos Achlioptas and Olga Diamanti and Ioannis Mitliagkas and Leonidas Guibas",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.mlr.press/v80/achlioptas18a.html",
      "doi": "",
      "arxiv": "1707.02392",
      "source": "manuscript/tables/catalogue-assets.tex:26",
      "project_url": "",
      "url": "https://proceedings.mlr.press/v80/achlioptas18a.html",
      "kind": "method",
      "input_tags": [
        "N"
      ],
      "inputs": [
        "Latent / random seed"
      ],
      "description": "GMM · Point-cloud latent · Point clouds",
      "fields": {
        "Input": "Latent / random seed",
        "Mechanism": "GMM",
        "Representation / state": "Point-cloud latent",
        "Output": "Point clouds",
        "Stage": "P"
      }
    },
    {
      "id": "A3",
      "name": "PointFlow",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Learned geometry and 3D-aware generation",
      "bibkey": "Yang2019PointFlow",
      "title": "PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows",
      "year": 2019,
      "venue": "Proceedings of the IEEE/CVF International Conference on Computer Vision",
      "authors": "Guandao Yang and Xun Huang and Zekun Hao and Ming-Yu Liu and Serge Belongie and Bharath Hariharan",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content_ICCV_2019/html/Yang_PointFlow_3D_Point_Cloud_Generation_With_Continuous_Normalizing_Flows_ICCV_2019_paper.html",
      "doi": "10.1109/iccv.2019.00464",
      "arxiv": "1906.12320",
      "source": "manuscript/tables/catalogue-assets.tex:28",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content_ICCV_2019/html/Yang_PointFlow_3D_Point_Cloud_Generation_With_Continuous_Normalizing_Flows_ICCV_2019_paper.html",
      "kind": "method",
      "input_tags": [
        "N"
      ],
      "inputs": [
        "Latent / random seed"
      ],
      "description": "NF · Shape/point distributions · Point clouds",
      "fields": {
        "Input": "Latent / random seed",
        "Mechanism": "NF",
        "Representation / state": "Shape/point distributions",
        "Output": "Point clouds",
        "Stage": "P"
      }
    },
    {
      "id": "A4",
      "name": "AtlasNet",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Learned geometry and 3D-aware generation",
      "bibkey": "Groueix2018AtlasNet",
      "title": "A Papier-Mâché Approach to Learning 3D Surface Generation",
      "year": 2018,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Thibault Groueix and Matthew Fisher and Vladimir G. Kim and Bryan C. Russell and Mathieu Aubry",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content_cvpr_2018/html/Groueix_A_Papier-Mache_Approach_CVPR_2018_paper.html",
      "doi": "10.1109/cvpr.2018.00030",
      "arxiv": "1802.05384",
      "source": "manuscript/tables/catalogue-assets.tex:29",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content_cvpr_2018/html/Groueix_A_Papier-Mache_Approach_CVPR_2018_paper.html",
      "kind": "method",
      "input_tags": [
        "I",
        "G"
      ],
      "inputs": [
        "Image",
        "Geometry"
      ],
      "description": "DEC · Parametric surface patches · Surface meshes",
      "fields": {
        "Input": "Image, Geometry",
        "Mechanism": "DEC",
        "Representation / state": "Parametric surface patches",
        "Output": "Surface meshes",
        "Stage": "P"
      }
    },
    {
      "id": "A5",
      "name": "DMTet",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Learned geometry and 3D-aware generation",
      "bibkey": "Shen2021DMTet",
      "title": "Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis",
      "year": 2021,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Tianchang Shen and Jun Gao and Kangxue Yin and Ming-Yu Liu and Sanja Fidler",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper_files/paper/2021/hash/30a237d18c50f563cba4531f1db44acf-Abstract.html",
      "doi": "",
      "arxiv": "2111.04276",
      "source": "manuscript/tables/catalogue-assets.tex:31",
      "project_url": "https://research.nvidia.com/labs/toronto-ai/DMTet/",
      "url": "https://research.nvidia.com/labs/toronto-ai/DMTet/",
      "kind": "method",
      "input_tags": [
        "G"
      ],
      "inputs": [
        "Geometry"
      ],
      "description": "GEN · Deformable tetrahedral SDF · Meshes",
      "fields": {
        "Input": "Geometry",
        "Mechanism": "GEN",
        "Representation / state": "Deformable tetrahedral SDF",
        "Output": "Meshes",
        "Stage": "P"
      }
    },
    {
      "id": "A6",
      "name": "GET3D",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Learned geometry and 3D-aware generation",
      "bibkey": "Gao2022GET3D",
      "title": "GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images",
      "year": 2022,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Jun Gao and Tianchang Shen and Zian Wang and Wenzheng Chen and Kangxue Yin and Daiqing Li and Or Litany and Zan Gojcic and Sanja Fidler",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper_files/paper/2022/hash/cebbd24f1e50bcb63d015611fe0fe767-Abstract-Conference.html",
      "doi": "",
      "arxiv": "2209.11163",
      "source": "manuscript/tables/catalogue-assets.tex:32",
      "project_url": "",
      "url": "https://proceedings.neurips.cc/paper_files/paper/2022/hash/cebbd24f1e50bcb63d015611fe0fe767-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "N"
      ],
      "inputs": [
        "Latent / random seed"
      ],
      "description": "GAN · Geometry/texture fields · Textured meshes",
      "fields": {
        "Input": "Latent / random seed",
        "Mechanism": "GAN",
        "Representation / state": "Geometry/texture fields",
        "Output": "Textured meshes",
        "Stage": "P"
      }
    },
    {
      "id": "A7",
      "name": "EG3D",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Learned geometry and 3D-aware generation",
      "bibkey": "Chan2022EG3D",
      "title": "Efficient Geometry-Aware 3D Generative Adversarial Networks",
      "year": 2022,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Eric R. Chan and Connor Z. Lin and Matthew A. Chan and Koki Nagano and Boxiao Pan and Shalini De Mello and Orazio Gallo and Leonidas J. Guibas and Jonathan Tremblay and Sameh Khamis and Tero Karras and Gordon Wetzstein",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2022/html/Chan_Efficient_Geometry-Aware_3D_Generative_Adversarial_Networks_CVPR_2022_paper.html",
      "doi": "10.1109/cvpr52688.2022.01565",
      "arxiv": "2112.07945",
      "source": "manuscript/tables/catalogue-assets.tex:34",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2022/html/Chan_Efficient_Geometry-Aware_3D_Generative_Adversarial_Networks_CVPR_2022_paper.html",
      "kind": "method",
      "input_tags": [
        "N",
        "P"
      ],
      "inputs": [
        "Latent / random seed",
        "Camera / pose"
      ],
      "description": "GAN · Triplane radiance field · Rendered images",
      "fields": {
        "Input": "Latent / random seed, Camera / pose",
        "Mechanism": "GAN",
        "Representation / state": "Triplane radiance field",
        "Output": "Rendered images",
        "Stage": "P"
      }
    },
    {
      "id": "A8",
      "name": "Dream Fields",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Optimization through image priors",
      "bibkey": "Jain2022DreamFields",
      "title": "Zero-Shot Text-Guided Object Generation With Dream Fields",
      "year": 2022,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Ajay Jain and Ben Mildenhall and Jonathan T. Barron and Pieter Abbeel and Ben Poole",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2022/html/Jain_Zero-Shot_Text-Guided_Object_Generation_With_Dream_Fields_CVPR_2022_paper.html",
      "doi": "10.1109/cvpr52688.2022.00094",
      "arxiv": "2112.01455",
      "source": "manuscript/tables/catalogue-assets.tex:36",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2022/html/Jain_Zero-Shot_Text-Guided_Object_Generation_With_Dream_Fields_CVPR_2022_paper.html",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "CLIP+OPT · Radiance field · Radiance field",
      "fields": {
        "Input": "Text",
        "Mechanism": "CLIP+OPT",
        "Representation / state": "Radiance field",
        "Output": "Radiance field",
        "Stage": "P"
      }
    },
    {
      "id": "A9",
      "name": "Text2Mesh",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Optimization through image priors",
      "bibkey": "Michel2022Text2Mesh",
      "title": "Text2Mesh: Text-Driven Neural Stylization for Meshes",
      "year": 2022,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Oscar Michel and Roi Bar-On and Richard Liu and Sagie Benaim and Rana Hanocka",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2022/html/Michel_Text2Mesh_Text-Driven_Neural_Stylization_for_Meshes_CVPR_2022_paper.html",
      "doi": "10.1109/cvpr52688.2022.01313",
      "arxiv": "2112.03221",
      "source": "manuscript/tables/catalogue-assets.tex:38",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2022/html/Michel_Text2Mesh_Text-Driven_Neural_Stylization_for_Meshes_CVPR_2022_paper.html",
      "kind": "method",
      "input_tags": [
        "T",
        "G"
      ],
      "inputs": [
        "Text",
        "Geometry"
      ],
      "description": "CLIP+OPT · Mesh/color/displacement · Edited mesh",
      "fields": {
        "Input": "Text, Geometry",
        "Mechanism": "CLIP+OPT",
        "Representation / state": "Mesh/color/displacement",
        "Output": "Edited mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A10",
      "name": "CLIP-Mesh",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Optimization through image priors",
      "bibkey": "Khalid2022CLIPMesh",
      "title": "CLIP-Mesh: Generating textured meshes from text using pretrained image-text models",
      "year": 2022,
      "venue": "SIGGRAPH Asia Conference Papers",
      "authors": "Mohammad Khalid, Nasir and Xie, Tianhao and Belilovsky, Eugene and Popa, Tiberiu",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1145/3550469.3555392",
      "doi": "10.1145/3550469.3555392",
      "arxiv": "2203.13333",
      "source": "manuscript/tables/catalogue-assets.tex:39",
      "project_url": "",
      "url": "https://doi.org/10.1145/3550469.3555392",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "CLIP+OPT · Mesh/texture/normal maps · Textured mesh",
      "fields": {
        "Input": "Text",
        "Mechanism": "CLIP+OPT",
        "Representation / state": "Mesh/texture/normal maps",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A11",
      "name": "DreamFusion",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Optimization through image priors",
      "bibkey": "Poole2023DreamFusion",
      "title": "DreamFusion: Text-to-3D using 2D Diffusion",
      "year": 2023,
      "venue": "The Eleventh International Conference on Learning Representations (ICLR)",
      "authors": "Ben Poole and Ajay Jain and Jonathan T. Barron and Ben Mildenhall",
      "publication_type": "venue_publication",
      "paper_url": "https://openreview.net/forum?id=FjNys5c7VyY",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-assets.tex:41",
      "project_url": "https://dreamfusion3d.github.io/",
      "url": "https://dreamfusion3d.github.io/",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "SDS · Density/albedo field · Mesh/renders",
      "fields": {
        "Input": "Text",
        "Mechanism": "SDS",
        "Representation / state": "Density/albedo field",
        "Output": "Mesh/renders",
        "Stage": "P"
      }
    },
    {
      "id": "A12",
      "name": "Magic3D",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Optimization through image priors",
      "bibkey": "Lin2023Magic3D",
      "title": "Magic3D: High-Resolution Text-to-3D Content Creation",
      "year": 2023,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
      "authors": "Chen-Hsuan Lin and Jun Gao and Luming Tang and Towaki Takikawa and Xiaohui Zeng and Xun Huang and Karsten Kreis and Sanja Fidler and Ming-Yu Liu and Tsung-Yi Lin",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1109/cvpr52729.2023.00037",
      "doi": "10.1109/cvpr52729.2023.00037",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-assets.tex:42",
      "project_url": "https://research.nvidia.com/labs/cosmos-lab/magic3d/",
      "url": "https://research.nvidia.com/labs/cosmos-lab/magic3d/",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "SDS · Hash-grid/mesh · Textured mesh",
      "fields": {
        "Input": "Text",
        "Mechanism": "SDS",
        "Representation / state": "Hash-grid/mesh",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A13",
      "name": "ProlificDreamer",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Optimization through image priors",
      "bibkey": "Wang2023ProlificDreamer",
      "title": "ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation",
      "year": 2023,
      "venue": "NeurIPS 2023",
      "authors": "Zhengyi Wang and Cheng Lu and Yikai Wang and Fan Bao and Chongxuan Li and Hang Su and Jun Zhu",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2305.16213",
      "doi": "",
      "arxiv": "2305.16213",
      "source": "manuscript/tables/catalogue-assets.tex:44",
      "project_url": "",
      "url": "https://arxiv.org/abs/2305.16213",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "VSD · 3D parameter particles · Textured mesh",
      "fields": {
        "Input": "Text",
        "Mechanism": "VSD",
        "Representation / state": "3D parameter particles",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A14",
      "name": "DreamGaussian",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Optimization through image priors",
      "bibkey": "Tang2024DreamGaussian",
      "title": "DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation",
      "year": 2024,
      "venue": "ICLR 2024",
      "authors": "Jiaxiang Tang and Jiawei Ren and Hang Zhou and Ziwei Liu and Gang Zeng",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.iclr.cc/paper_files/paper/2024/hash/905202e21386913d8eac637c2b50f590-Abstract-Conference.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-assets.tex:45",
      "project_url": "",
      "url": "https://proceedings.iclr.cc/paper_files/paper/2024/hash/905202e21386913d8eac637c2b50f590-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "SD · 3D Gaussians · Textured mesh",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "SD",
        "Representation / state": "3D Gaussians",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A15",
      "name": "Zero-1-to-3",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "View synthesis and feed-forward reconstruction",
      "bibkey": "Liu2023Zero123",
      "title": "Zero-1-to-3: Zero-shot One Image to 3D Object",
      "year": 2023,
      "venue": "ICCV 2023",
      "authors": "Ruoshi Liu and Rundi Wu and Van Hoorick, Basile and Pavel Tokmakov and Sergey Zakharov and Carl Vondrick",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/ICCV2023/html/Liu_Zero-1-to-3_Zero-shot_One_Image_to_3D_Object_ICCV_2023_paper.html",
      "doi": "10.1109/iccv51070.2023.00853",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-assets.tex:48",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/ICCV2023/html/Liu_Zero-1-to-3_Zero-shot_One_Image_to_3D_Object_ICCV_2023_paper.html",
      "kind": "method",
      "input_tags": [
        "I",
        "P"
      ],
      "inputs": [
        "Image",
        "Camera / pose"
      ],
      "description": "Diff. · Image latents · Novel-view images",
      "fields": {
        "Input": "Image, Camera / pose",
        "Mechanism": "Diff.",
        "Representation / state": "Image latents",
        "Output": "Novel-view images",
        "Stage": "P"
      }
    },
    {
      "id": "A16",
      "name": "SyncDreamer",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "View synthesis and feed-forward reconstruction",
      "bibkey": "Liu2024SyncDreamer",
      "title": "SyncDreamer: Generating Multiview-consistent Images from a Single-view Image",
      "year": 2024,
      "venue": "ICLR 2024",
      "authors": "Yuan Liu and Cheng Lin and Zijiao Zeng and Xiaoxiao Long and Lingjie Liu and Taku Komura and Wenping Wang",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2309.03453",
      "doi": "",
      "arxiv": "2309.03453",
      "source": "manuscript/tables/catalogue-assets.tex:49",
      "project_url": "",
      "url": "https://arxiv.org/abs/2309.03453",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "Diff. · Coupled image latents · Multiview images",
      "fields": {
        "Input": "Image",
        "Mechanism": "Diff.",
        "Representation / state": "Coupled image latents",
        "Output": "Multiview images",
        "Stage": "P"
      }
    },
    {
      "id": "A17",
      "name": "MVDream",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "View synthesis and feed-forward reconstruction",
      "bibkey": "Shi2024MVDream",
      "title": "MVDream: Multi-view Diffusion for 3D Generation",
      "year": 2024,
      "venue": "ICLR 2024",
      "authors": "Yichun Shi and Peng Wang and Jianglong Ye and Long Mai and Kejie Li and Xiao Yang",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.iclr.cc/paper_files/paper/2024/hash/adbe936993aa7cf41e45054d8b72f183-Abstract-Conference.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-assets.tex:51",
      "project_url": "",
      "url": "https://proceedings.iclr.cc/paper_files/paper/2024/hash/adbe936993aa7cf41e45054d8b72f183-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "T",
        "P"
      ],
      "inputs": [
        "Text",
        "Camera / pose"
      ],
      "description": "Diff. · Multiview image latents · Multiview images",
      "fields": {
        "Input": "Text, Camera / pose",
        "Mechanism": "Diff.",
        "Representation / state": "Multiview image latents",
        "Output": "Multiview images",
        "Stage": "P"
      }
    },
    {
      "id": "A18",
      "name": "Zero123++",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "View synthesis and feed-forward reconstruction",
      "bibkey": "Shi2023Zero123Plus",
      "title": "Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model",
      "year": 2023,
      "venue": "arXiv",
      "authors": "Ruoxi Shi and Hansheng Chen and Zhuoyang Zhang and Minghua Liu and Chao Xu and Xinyue Wei and Linghao Chen and Chong Zeng and Hao Su",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2310.15110",
      "doi": "",
      "arxiv": "2310.15110",
      "source": "manuscript/tables/catalogue-assets.tex:52",
      "project_url": "",
      "url": "https://arxiv.org/abs/2310.15110",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "Diff. · Multiview image latents · Multiview images",
      "fields": {
        "Input": "Image",
        "Mechanism": "Diff.",
        "Representation / state": "Multiview image latents",
        "Output": "Multiview images",
        "Stage": "P"
      }
    },
    {
      "id": "A19",
      "name": "Wonder3D",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "View synthesis and feed-forward reconstruction",
      "bibkey": "Long2024Wonder3D",
      "title": "Wonder3D: Single Image to 3D using Cross-Domain Diffusion",
      "year": 2024,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Xiaoxiao Long and Yuan-Chen Guo and Cheng Lin and Yuan Liu and Zhiyang Dou and Lingjie Liu and Yuexin Ma and Song-Hai Zhang and Marc Habermann and Christian Theobalt and Wenping Wang",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Long_Wonder3D_Single_Image_to_3D_using_Cross-Domain_Diffusion_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.00951",
      "arxiv": "2310.15008",
      "source": "manuscript/tables/catalogue-assets.tex:54",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Long_Wonder3D_Single_Image_to_3D_using_Cross-Domain_Diffusion_CVPR_2024_paper.html",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "Diff. · Multiview color/normals · Textured mesh",
      "fields": {
        "Input": "Image",
        "Mechanism": "Diff.",
        "Representation / state": "Multiview color/normals",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A20",
      "name": "Unique3D",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "View synthesis and feed-forward reconstruction",
      "bibkey": "Wu2024Unique3D",
      "title": "Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image",
      "year": 2024,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Kailu Wu and Fangfu Liu and Zhihan Cai and Runjie Yan and Hanyang Wang and Yating Hu and Yueqi Duan and Kaisheng Ma",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/e25198b6a75f74277ee3a2bd4165d9ef-Abstract-Conference.html",
      "doi": "10.52202/079017-3974",
      "arxiv": "2405.20343",
      "source": "manuscript/tables/catalogue-assets.tex:55",
      "project_url": "",
      "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/e25198b6a75f74277ee3a2bd4165d9ef-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "Diff.+REC · Multiview color/normals · Textured mesh",
      "fields": {
        "Input": "Image",
        "Mechanism": "Diff.+REC",
        "Representation / state": "Multiview color/normals",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A21",
      "name": "Magic123",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "View synthesis and feed-forward reconstruction",
      "bibkey": "Qian2024Magic123",
      "title": "Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors",
      "year": 2024,
      "venue": "International Conference on Learning Representations",
      "authors": "Guocheng Qian and Jinjie Mai and Abdullah Hamdi and Jian Ren and Aliaksandr Siarohin and Bing Li and Hsin-Ying Lee and Ivan Skorokhodov and Peter Wonka and Sergey Tulyakov and Bernard Ghanem",
      "publication_type": "venue_publication",
      "paper_url": "https://guochengqian.github.io/project/magic123/",
      "doi": "",
      "arxiv": "2306.17843",
      "source": "manuscript/tables/catalogue-assets.tex:57",
      "project_url": "",
      "url": "https://guochengqian.github.io/project/magic123/",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "Diff.+OPT · Radiance-field/mesh · Textured mesh",
      "fields": {
        "Input": "Image",
        "Mechanism": "Diff.+OPT",
        "Representation / state": "Radiance-field/mesh",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A22",
      "name": "One-2-3-45",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "View synthesis and feed-forward reconstruction",
      "bibkey": "Liu2023One2345",
      "title": "One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization",
      "year": 2023,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Minghua Liu and Chao Xu and Haian Jin and Linghao Chen and Mukund Varma T and Zexiang Xu and Hao Su",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/4683beb6bab325650db13afd05d1a14a-Abstract-Conference.html",
      "doi": "",
      "arxiv": "2306.16928",
      "source": "manuscript/tables/catalogue-assets.tex:58",
      "project_url": "",
      "url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/4683beb6bab325650db13afd05d1a14a-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "Diff.+REC · Multiview/SDF · Textured mesh",
      "fields": {
        "Input": "Image",
        "Mechanism": "Diff.+REC",
        "Representation / state": "Multiview/SDF",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A23",
      "name": "One-2-3-45++",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "View synthesis and feed-forward reconstruction",
      "bibkey": "Liu2024One2345Plus",
      "title": "One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion",
      "year": 2024,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Minghua Liu and Ruoxi Shi and Linghao Chen and Zhuoyang Zhang and Chao Xu and Xinyue Wei and Hansheng Chen and Chong Zeng and Jiayuan Gu and Hao Su",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Liu_One-2-3-45_Fast_Single_Image_to_3D_Objects_with_Consistent_Multi-View_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.00960",
      "arxiv": "2311.07885",
      "source": "manuscript/tables/catalogue-assets.tex:60",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Liu_One-2-3-45_Fast_Single_Image_to_3D_Objects_with_Consistent_Multi-View_CVPR_2024_paper.html",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "Diff. · 3D diffusion latents · Textured mesh",
      "fields": {
        "Input": "Image",
        "Mechanism": "Diff.",
        "Representation / state": "3D diffusion latents",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A24",
      "name": "LRM",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "View synthesis and feed-forward reconstruction",
      "bibkey": "Hong2024LRM",
      "title": "LRM: Large Reconstruction Model for Single Image to 3D",
      "year": 2024,
      "venue": "ICLR 2024",
      "authors": "Yicong Hong and Kai Zhang and Jiuxiang Gu and Sai Bi and Yang Zhou and Difan Liu and Feng Liu and Kalyan Sunkavalli and Trung Bui and Hao Tan",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2311.04400",
      "doi": "",
      "arxiv": "2311.04400",
      "source": "manuscript/tables/catalogue-assets.tex:61",
      "project_url": "",
      "url": "https://arxiv.org/abs/2311.04400",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "REC · Triplane radiance field · Radiance field",
      "fields": {
        "Input": "Image",
        "Mechanism": "REC",
        "Representation / state": "Triplane radiance field",
        "Output": "Radiance field",
        "Stage": "P"
      }
    },
    {
      "id": "A25",
      "name": "InstantMesh",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "View synthesis and feed-forward reconstruction",
      "bibkey": "Xu2024InstantMesh",
      "title": "InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models",
      "year": 2024,
      "venue": "arXiv",
      "authors": "Jiale Xu and Weihao Cheng and Yiming Gao and Xintao Wang and Shenghua Gao and Ying Shan",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2404.07191",
      "doi": "",
      "arxiv": "2404.07191",
      "source": "manuscript/tables/catalogue-assets.tex:63",
      "project_url": "",
      "url": "https://arxiv.org/abs/2404.07191",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "Diff.+REC · Triplane/isosurface · Textured mesh",
      "fields": {
        "Input": "Image",
        "Mechanism": "Diff.+REC",
        "Representation / state": "Triplane/isosurface",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A26",
      "name": "LGM",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "View synthesis and feed-forward reconstruction",
      "bibkey": "Tang2024LGM",
      "title": "LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation",
      "year": 2024,
      "venue": "ECCV 2024",
      "authors": "Jiaxiang Tang and Zhaoxi Chen and Xiaokang Chen and Tengfei Wang and Gang Zeng and Ziwei Liu",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2402.05054",
      "doi": "10.1007/978-3-031-73235-5_1",
      "arxiv": "2402.05054",
      "source": "manuscript/tables/catalogue-assets.tex:64",
      "project_url": "",
      "url": "https://arxiv.org/abs/2402.05054",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "REC · 3D Gaussians · Gaussian asset",
      "fields": {
        "Input": "Image",
        "Mechanism": "REC",
        "Representation / state": "3D Gaussians",
        "Output": "Gaussian asset",
        "Stage": "P"
      }
    },
    {
      "id": "A27",
      "name": "GRM",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "View synthesis and feed-forward reconstruction",
      "bibkey": "Xu2024GRM",
      "title": "GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation",
      "year": 2024,
      "venue": "ECCV 2024",
      "authors": "Yinghao Xu and Zifan Shi and Wang, Yifan and Hansheng Chen and Ceyuan Yang and Sida Peng and Yujun Shen and Gordon Wetzstein",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2403.14621",
      "doi": "10.1007/978-3-031-72633-0_1",
      "arxiv": "2403.14621",
      "source": "manuscript/tables/catalogue-assets.tex:66",
      "project_url": "",
      "url": "https://arxiv.org/abs/2403.14621",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "REC · Pixel-aligned Gaussians · Gaussian asset",
      "fields": {
        "Input": "Image",
        "Mechanism": "REC",
        "Representation / state": "Pixel-aligned Gaussians",
        "Output": "Gaussian asset",
        "Stage": "P"
      }
    },
    {
      "id": "A28",
      "name": "LION",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Native 3D and shape/appearance generation",
      "bibkey": "Zeng2022LION",
      "title": "LION: Latent Point Diffusion Models for 3D Shape Generation",
      "year": 2022,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Xiaohui Zeng and Arash Vahdat and Francis Williams and Zan Gojcic and Or Litany and Sanja Fidler and Karsten Kreis",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper_files/paper/2022/hash/40e56dabe12095a5fc44a6e4c3835948-Abstract-Conference.html",
      "doi": "",
      "arxiv": "2210.06978",
      "source": "manuscript/tables/catalogue-assets.tex:68",
      "project_url": "",
      "url": "https://proceedings.neurips.cc/paper_files/paper/2022/hash/40e56dabe12095a5fc44a6e4c3835948-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "N"
      ],
      "inputs": [
        "Latent / random seed"
      ],
      "description": "Diff. · Global/point latents · Point clouds",
      "fields": {
        "Input": "Latent / random seed",
        "Mechanism": "Diff.",
        "Representation / state": "Global/point latents",
        "Output": "Point clouds",
        "Stage": "P"
      }
    },
    {
      "id": "A29",
      "name": "SDFusion",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Native 3D and shape/appearance generation",
      "bibkey": "Cheng2023SDFusion",
      "title": "SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation",
      "year": 2023,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Yen-Chi Cheng and Hsin-Ying Lee and Sergey Tulyakov and Alexander G. Schwing and Liang-Yan Gui",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2023/html/Cheng_SDFusion_Multimodal_3D_Shape_Completion_Reconstruction_and_Generation_CVPR_2023_paper.html",
      "doi": "10.1109/cvpr52729.2023.00433",
      "arxiv": "2212.04493",
      "source": "manuscript/tables/catalogue-assets.tex:70",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2023/html/Cheng_SDFusion_Multimodal_3D_Shape_Completion_Reconstruction_and_Generation_CVPR_2023_paper.html",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "G"
      ],
      "inputs": [
        "Text",
        "Image",
        "Geometry"
      ],
      "description": "Diff. · SDF latent grid · Meshes",
      "fields": {
        "Input": "Text, Image, Geometry",
        "Mechanism": "Diff.",
        "Representation / state": "SDF latent grid",
        "Output": "Meshes",
        "Stage": "P"
      }
    },
    {
      "id": "A30",
      "name": "MeshDiffusion",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Native 3D and shape/appearance generation",
      "bibkey": "Liu2023MeshDiffusion",
      "title": "MeshDiffusion: Score-based Generative 3D Mesh Modeling",
      "year": 2023,
      "venue": "International Conference on Learning Representations",
      "authors": "Zhen Liu and Yao Feng and Michael J. Black and Derek Nowrouzezahrai and Liam Paull and Weiyang Liu",
      "publication_type": "venue_publication",
      "paper_url": "https://meshdiffusion.github.io/",
      "doi": "",
      "arxiv": "2303.08133",
      "source": "manuscript/tables/catalogue-assets.tex:71",
      "project_url": "",
      "url": "https://meshdiffusion.github.io/",
      "kind": "method",
      "input_tags": [
        "N"
      ],
      "inputs": [
        "Latent / random seed"
      ],
      "description": "Diff. · Deformable tetrahedral SDF · Meshes",
      "fields": {
        "Input": "Latent / random seed",
        "Mechanism": "Diff.",
        "Representation / state": "Deformable tetrahedral SDF",
        "Output": "Meshes",
        "Stage": "P"
      }
    },
    {
      "id": "A31",
      "name": "TRELLIS",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Native 3D and shape/appearance generation",
      "bibkey": "Xiang2025TRELLIS",
      "title": "Structured 3D Latents for Scalable and Versatile 3D Generation",
      "year": 2025,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
      "authors": "Jianfeng Xiang and Zelong Lv and Sicheng Xu and Yu Deng and Ruicheng Wang and Bowen Zhang and Dong Chen and Xin Tong and Jiaolong Yang",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1109/cvpr52734.2025.02000",
      "doi": "10.1109/cvpr52734.2025.02000",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-assets.tex:73",
      "project_url": "https://microsoft.github.io/TRELLIS/",
      "url": "https://microsoft.github.io/TRELLIS/",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "RF · Sparse structured latent · Mesh/field/Gaussians",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "RF",
        "Representation / state": "Sparse structured latent",
        "Output": "Mesh/field/Gaussians",
        "Stage": "P"
      }
    },
    {
      "id": "A32",
      "name": "Shap-E",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Native 3D and shape/appearance generation",
      "bibkey": "Jun2023ShapE",
      "title": "Shap-E: Generating Conditional 3D Implicit Functions",
      "year": 2023,
      "venue": "arXiv",
      "authors": "Heewoo Jun and Alex Nichol",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2305.02463",
      "doi": "",
      "arxiv": "2305.02463",
      "source": "manuscript/tables/catalogue-assets.tex:74",
      "project_url": "",
      "url": "https://arxiv.org/abs/2305.02463",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "Diff. · Implicit-function parameters · Mesh/radiance field",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "Diff.",
        "Representation / state": "Implicit-function parameters",
        "Output": "Mesh/radiance field",
        "Stage": "P"
      }
    },
    {
      "id": "A33",
      "name": "LN3Diff",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Native 3D and shape/appearance generation",
      "bibkey": "Lan2024LN3Diff",
      "title": "LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation",
      "year": 2024,
      "venue": "ECCV 2024",
      "authors": "Yushi Lan and Fangzhou Hong and Shuai Yang and Shangchen Zhou and Xuyi Meng and Bo Dai and Xingang Pan and Chen Change Loy",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2403.12019v2",
      "doi": "10.1007/978-3-031-73235-5_7",
      "arxiv": "2403.12019",
      "source": "manuscript/tables/catalogue-assets.tex:76",
      "project_url": "",
      "url": "https://arxiv.org/abs/2403.12019v2",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "Diff. · 3D-aware latent · Neural field",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "Diff.",
        "Representation / state": "3D-aware latent",
        "Output": "Neural field",
        "Stage": "P"
      }
    },
    {
      "id": "A34",
      "name": "3DTopia-XL",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Native 3D and shape/appearance generation",
      "bibkey": "Chen2025ThreeDTopiaXL",
      "title": "3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion",
      "year": 2025,
      "venue": "CVPR 2025",
      "authors": "Zhaoxi Chen and Jiaxiang Tang and Yuhao Dong and Ziang Cao and Fangzhou Hong and Yushi Lan and Tengfei Wang and Haozhe Xie and Tong Wu and Shunsuke Saito and Liang Pan and Dahua Lin and Ziwei Liu",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2409.12957",
      "doi": "10.1109/cvpr52734.2025.02475",
      "arxiv": "2409.12957",
      "source": "manuscript/tables/catalogue-assets.tex:77",
      "project_url": "",
      "url": "https://arxiv.org/abs/2409.12957",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "Diff. · Geometry/material primitives · PBR mesh",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "Diff.",
        "Representation / state": "Geometry/material primitives",
        "Output": "PBR mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A35",
      "name": "Hunyuan3D 2.0",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Native 3D and shape/appearance generation",
      "bibkey": "Zhao2025Hunyuan3D2",
      "title": "Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation",
      "year": 2025,
      "venue": "arXiv",
      "authors": "Zibo Zhao and Zeqiang Lai and Qingxiang Lin and Yunfei Zhao and Haolin Liu and Shuhui Yang and Yifei Feng and Mingxin Yang and Sheng Zhang and Xianghui Yang and Huiwen Shi and Sicong Liu and Junta Wu and Yihang Lian and Fan Yang and Ruining Tang and Zebin He and Xinzhou Wang and Jian Liu and Xuhui Zuo and Zhuo Chen and Biwen Lei and Haohan Weng and Jing Xu and Yiling Zhu and Xinhai Liu and Lixin Xu and Changrong Hu and Tianyu Huang and Lifu Wang and Jihong Zhang and Meng Chen and Liang Dong and Yiwen Jia and Yulin Cai and Jiaao Yu and Yixuan Tang and Hao Zhang and Zheng Ye and Peng He and Runzhou Wu and Chao Zhang and Yonghao Tan and Jie Xiao and Yangyu Tao and Jianchen Zhu and Jinbao Xue and Kai Liu and Chongqing Zhao and Xinming Wu and Zhichao Hu and Lei Qin and Jianbing Peng and Zhan Li and Minghui Chen and Xipeng Zhang and Lin Niu and Paige Wang and Yingkai Wang and Haozhao Kuang and Zhongyi Fan and Xu Zheng and Weihao Zhuang and YingPing He and Tian Liu and Yong Yang and Di Wang and Yuhong Liu and Jie Jiang and Jingwei Huang and Chunchao Guo",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2501.12202v1",
      "doi": "10.48550/arXiv.2501.12202",
      "arxiv": "2501.12202",
      "source": "manuscript/tables/catalogue-assets.tex:79",
      "project_url": "https://3d-models.hunyuan.tencent.com/?currentTab=hy-model-v2",
      "url": "https://3d-models.hunyuan.tencent.com/?currentTab=hy-model-v2",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "FM+Diff. · Shape latents/mesh · Textured mesh",
      "fields": {
        "Input": "Image",
        "Mechanism": "FM+Diff.",
        "Representation / state": "Shape latents/mesh",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A36",
      "name": "TRELLIS.2",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Native 3D and shape/appearance generation",
      "bibkey": "Xiang2026TRELLIS2",
      "title": "Native and Compact Structured Latents for 3D Generation",
      "year": 2026,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
      "authors": "Jianfeng Xiang and Xiaoxue Chen and Sicheng Xu and Ruicheng Wang and Zelong Lv and Yu Deng and Hongyuan Zhu and Yue Dong and Hao Zhao and Nicholas Jing Yuan and Jiaolong Yang",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2026/html/Xiang_Native_and_Compact_Structured_Latents_for_3D_Generation_CVPR_2026_paper.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-assets.tex:80",
      "project_url": "https://microsoft.github.io/TRELLIS.2/",
      "url": "https://microsoft.github.io/TRELLIS.2/",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "RF · O-Voxel latents · PBR mesh",
      "fields": {
        "Input": "Image",
        "Mechanism": "RF",
        "Representation / state": "O-Voxel latents",
        "Output": "PBR mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A37",
      "name": "Fantasia3D",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Native 3D and shape/appearance generation",
      "bibkey": "Chen2023Fantasia3D",
      "title": "Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation",
      "year": 2023,
      "venue": "ICCV 2023",
      "authors": "Rui Chen and Yongwei Chen and Ningxin Jiao and Kui Jia",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2303.13873",
      "doi": "10.1109/iccv51070.2023.02033",
      "arxiv": "2303.13873",
      "source": "manuscript/tables/catalogue-assets.tex:82",
      "project_url": "",
      "url": "https://arxiv.org/abs/2303.13873",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "SD · Geometry/BRDF fields · PBR mesh",
      "fields": {
        "Input": "Text",
        "Mechanism": "SD",
        "Representation / state": "Geometry/BRDF fields",
        "Output": "PBR mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A38",
      "name": "TripoSG",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Native 3D and shape/appearance generation",
      "bibkey": "Li2025TripoSG",
      "title": "TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models",
      "year": 2025,
      "venue": "arXiv",
      "authors": "Yangguang Li and Zi-Xin Zou and Zexiang Liu and Dehu Wang and Yuan Liang and Zhipeng Yu and Xingchao Liu and Yuan-Chen Guo and Ding Liang and Wanli Ouyang and Yan-Pei Cao",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2502.06608",
      "doi": "",
      "arxiv": "2502.06608",
      "source": "manuscript/tables/catalogue-assets.tex:83",
      "project_url": "",
      "url": "https://arxiv.org/abs/2502.06608",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "RF · SDF shape latents · Mesh",
      "fields": {
        "Input": "Image",
        "Mechanism": "RF",
        "Representation / state": "SDF shape latents",
        "Output": "Mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A39",
      "name": "Seed3D 2.0",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Native 3D and shape/appearance generation",
      "bibkey": "Gu2026Seed3D2",
      "title": "Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation",
      "year": 2026,
      "venue": "arXiv",
      "authors": "Gu, Diandian and Lin, Jing and Liu, Gaohong and Liu, Jiahang and Ma, Su and Shi, Guang and Wang, Jun and Wang, Qinlong and Wu, Qianyi and Xu, Zhongcong and Yi, Xuanyu and Yu, Zihao and Zhang, Jianfeng and Zheng, Zhuolin and Zhu, Yifan and Chen, Rui and Guo, Hengkai and Guo, Xiaoyang and Han, Mingcong and Han, Xu and Li, Xiu and Liang, Yixun and Lou, Weiqiang and Lu, Junzhe and Luo, Guan and Qin, Minghan and Wang, Shuguang and Wang, Yuang",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2605.13862",
      "doi": "10.48550/arXiv.2605.13862",
      "arxiv": "2605.13862",
      "source": "manuscript/tables/catalogue-assets.tex:85",
      "project_url": "https://seed.bytedance.com/en/seed3d_2_0",
      "url": "https://seed.bytedance.com/en/seed3d_2_0",
      "kind": "method",
      "input_tags": [
        "I",
        "G"
      ],
      "inputs": [
        "Image",
        "Geometry"
      ],
      "description": "Diff. · Shape vecsets /PBR latents · PBR mesh /optional URDF",
      "fields": {
        "Input": "Image, Geometry",
        "Mechanism": "Diff.",
        "Representation / state": "Shape vecsets /PBR latents",
        "Output": "PBR mesh /optional URDF",
        "Stage": "P"
      }
    },
    {
      "id": "A40",
      "name": "TEXTure",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Textures and materials",
      "bibkey": "Richardson2023TEXTure",
      "title": "TEXTure: Text-Guided Texturing of 3D Shapes",
      "year": 2023,
      "venue": "SIGGRAPH 2023 Conference Papers",
      "authors": "Elad Richardson and Gal Metzer and Yuval Alaluf and Raja Giryes and Daniel Cohen-Or",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2302.01721",
      "doi": "10.1145/3588432.3591503",
      "arxiv": "2302.01721",
      "source": "manuscript/tables/catalogue-assets.tex:87",
      "project_url": "",
      "url": "https://arxiv.org/abs/2302.01721",
      "kind": "method",
      "input_tags": [
        "T",
        "G"
      ],
      "inputs": [
        "Text",
        "Geometry"
      ],
      "description": "Diff. · Mesh/texture atlas · Textured mesh",
      "fields": {
        "Input": "Text, Geometry",
        "Mechanism": "Diff.",
        "Representation / state": "Mesh/texture atlas",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A41",
      "name": "Text2Tex",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Textures and materials",
      "bibkey": "Chen2023Text2Tex",
      "title": "Text2Tex: Text-driven Texture Synthesis via Diffusion Models",
      "year": 2023,
      "venue": "Proceedings of the IEEE/CVF International Conference on Computer Vision",
      "authors": "Dave Zhenyu Chen and Yawar Siddiqui and Hsin-Ying Lee and Sergey Tulyakov and Matthias Nießner",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/ICCV2023/html/Chen_Text2Tex_Text-driven_Texture_Synthesis_via_Diffusion_Models_ICCV_2023_paper.html",
      "doi": "10.1109/iccv51070.2023.01701",
      "arxiv": "2303.11396",
      "source": "manuscript/tables/catalogue-assets.tex:89",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/ICCV2023/html/Chen_Text2Tex_Text-driven_Texture_Synthesis_via_Diffusion_Models_ICCV_2023_paper.html",
      "kind": "method",
      "input_tags": [
        "T",
        "G"
      ],
      "inputs": [
        "Text",
        "Geometry"
      ],
      "description": "Diff.+INP · Mesh/texture atlas · Textured mesh",
      "fields": {
        "Input": "Text, Geometry",
        "Mechanism": "Diff.+INP",
        "Representation / state": "Mesh/texture atlas",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A42",
      "name": "Paint3D",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Textures and materials",
      "bibkey": "Zeng2024Paint3D",
      "title": "Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models",
      "year": 2024,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Xianfang Zeng and Xin Chen and Zhongqi Qi and Wen Liu and Zibo Zhao and Zhibin Wang and Bin Fu and Yong Liu and Gang Yu",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Zeng_Paint3D_Paint_Anything_3D_with_Lighting-Less_Texture_Diffusion_Models_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.00407",
      "arxiv": "2312.13913",
      "source": "manuscript/tables/catalogue-assets.tex:90",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Zeng_Paint3D_Paint_Anything_3D_with_Lighting-Less_Texture_Diffusion_Models_CVPR_2024_paper.html",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "G"
      ],
      "inputs": [
        "Text",
        "Image",
        "Geometry"
      ],
      "description": "Diff. · Mesh/UV texture · Textured mesh",
      "fields": {
        "Input": "Text, Image, Geometry",
        "Mechanism": "Diff.",
        "Representation / state": "Mesh/UV texture",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "A43",
      "name": "SceneTex",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Textures and materials",
      "bibkey": "Chen2024SceneTex",
      "title": "SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors",
      "year": 2024,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Dave Zhenyu Chen and Haoxuan Li and Hsin-Ying Lee and Sergey Tulyakov and Matthias Nießner",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Chen_SceneTex_High-Quality_Texture_Synthesis_for_Indoor_Scenes_via_Diffusion_Priors_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.01992",
      "arxiv": "2311.17261",
      "source": "manuscript/tables/catalogue-assets.tex:92",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Chen_SceneTex_High-Quality_Texture_Synthesis_for_Indoor_Scenes_via_Diffusion_Priors_CVPR_2024_paper.html",
      "kind": "method",
      "input_tags": [
        "T",
        "G"
      ],
      "inputs": [
        "Text",
        "Geometry"
      ],
      "description": "Diff.+OPT · Multiresolution texture field · Textured scene",
      "fields": {
        "Input": "Text, Geometry",
        "Mechanism": "Diff.+OPT",
        "Representation / state": "Multiresolution texture field",
        "Output": "Textured scene",
        "Stage": "P"
      }
    },
    {
      "id": "A44",
      "name": "MaterialApprentice",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Textures and materials",
      "bibkey": "Gupta2026MaterialApprentice",
      "title": "Reflecting Process Expertise in Procedural Material Generation",
      "year": 2026,
      "venue": "Computer Vision – ECCV 2026",
      "authors": "Gupta, Kunal and Joshi, Gaurav and Chen, Yen-Ru and Jain, Seemandhar and Mehta, Ishit and Chandraker, Manmohan",
      "publication_type": "venue_publication",
      "paper_url": "https://link.springer.com/chapter/10.1007/978-3-032-37281-9_19",
      "doi": "10.1007/978-3-032-37281-9_19",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-assets.tex:93",
      "project_url": "https://materialapprentice.github.io/",
      "url": "https://materialapprentice.github.io/",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "LLM+PROC · Process traces /shader graph · Procedural material graph",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "LLM+PROC",
        "Representation / state": "Process traces /shader graph",
        "Output": "Procedural material graph",
        "Stage": "P/A"
      }
    },
    {
      "id": "A45",
      "name": "PartCrafter",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Parts and explicit mesh structure",
      "bibkey": "Lin2025PartCrafter",
      "title": "PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers",
      "year": 2025,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Yuchen Lin and Chenguo Lin and Panwang Pan and Honglei Yan and Yiqiang Feng and Yadong Mu and Katerina Fragkiadaki",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper_files/paper/2025/hash/32cc61322f1e2f56f989d29ccc7cfbb7-Abstract-Conference.html",
      "doi": "10.52202/085713-1189",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-assets.tex:96",
      "project_url": "https://wgsxm.github.io/projects/partcrafter/",
      "url": "https://wgsxm.github.io/projects/partcrafter/",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image",
        "Requested part count (n)"
      ],
      "description": "FM · Part-indexed latent sets · Separate part meshes",
      "fields": {
        "Input": "Image, Requested part count (n)",
        "Mechanism": "FM",
        "Representation / state": "Part-indexed latent sets",
        "Output": "Separate part meshes",
        "Stage": "P"
      }
    },
    {
      "id": "A46",
      "name": "HoloPart",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Parts and explicit mesh structure",
      "bibkey": "Yang2025HoloPart",
      "title": "HoloPart: Generative 3D Part Amodal Segmentation",
      "year": 2025,
      "venue": "arXiv",
      "authors": "Yunhan Yang and Yuan-Chen Guo and Yukun Huang and Zi-Xin Zou and Zhipeng Yu and Yangguang Li and Yan-Pei Cao and Xihui Liu",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2504.07943",
      "doi": "",
      "arxiv": "2504.07943",
      "source": "manuscript/tables/catalogue-assets.tex:97",
      "project_url": "",
      "url": "https://arxiv.org/abs/2504.07943",
      "kind": "method",
      "input_tags": [
        "G"
      ],
      "inputs": [
        "Geometry"
      ],
      "description": "SEG+Diff. · Part latents · Completed part meshes",
      "fields": {
        "Input": "Geometry",
        "Mechanism": "SEG+Diff.",
        "Representation / state": "Part latents",
        "Output": "Completed part meshes",
        "Stage": "P"
      }
    },
    {
      "id": "A47",
      "name": "PolyGen",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Parts and explicit mesh structure",
      "bibkey": "Nash2020PolyGen",
      "title": "PolyGen: An Autoregressive Generative Model of 3D Meshes",
      "year": 2020,
      "venue": "Proceedings of the International Conference on Machine Learning",
      "authors": "Charlie Nash and Yaroslav Ganin and S. M. Ali Eslami and Peter Battaglia",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.mlr.press/v119/nash20a.html",
      "doi": "",
      "arxiv": "2002.10880",
      "source": "manuscript/tables/catalogue-assets.tex:99",
      "project_url": "",
      "url": "https://proceedings.mlr.press/v119/nash20a.html",
      "kind": "method",
      "input_tags": [
        "I",
        "G"
      ],
      "inputs": [
        "Image",
        "Geometry"
      ],
      "description": "AR · Vertex/face sequences · Polygon meshes",
      "fields": {
        "Input": "Image, Geometry",
        "Mechanism": "AR",
        "Representation / state": "Vertex/face sequences",
        "Output": "Polygon meshes",
        "Stage": "P"
      }
    },
    {
      "id": "A48",
      "name": "MeshGPT",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Parts and explicit mesh structure",
      "bibkey": "Siddiqui2024MeshGPT",
      "title": "MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers",
      "year": 2024,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Yawar Siddiqui and Antonio Alliegro and Alexey Artemov and Tatiana Tommasi and Daniele Sirigatti and Vladislav Rosov and Angela Dai and Matthias Nießner",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Siddiqui_MeshGPT_Generating_Triangle_Meshes_with_Decoder-Only_Transformers_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.01855",
      "arxiv": "2311.15475",
      "source": "manuscript/tables/catalogue-assets.tex:100",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Siddiqui_MeshGPT_Generating_Triangle_Meshes_with_Decoder-Only_Transformers_CVPR_2024_paper.html",
      "kind": "method",
      "input_tags": [
        "U"
      ],
      "inputs": [
        "Unconditional"
      ],
      "description": "AR · Quantized mesh tokens · Triangle meshes",
      "fields": {
        "Input": "Unconditional",
        "Mechanism": "AR",
        "Representation / state": "Quantized mesh tokens",
        "Output": "Triangle meshes",
        "Stage": "P"
      }
    },
    {
      "id": "A49",
      "name": "MeshAnything",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Parts and explicit mesh structure",
      "bibkey": "Chen2025MeshAnything",
      "title": "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers",
      "year": 2025,
      "venue": "International Conference on Learning Representations",
      "authors": "Yiwen Chen and Tong He and Di Huang and Weicai Ye and Sijin Chen and Jiaxiang Tang and Zhongang Cai and Lei Yang and Gang Yu and Guosheng Lin and Chi Zhang",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/7fc69f53a6ca2664ef23a9597903ca6f-Abstract-Conference.html",
      "doi": "",
      "arxiv": "2406.10163",
      "source": "manuscript/tables/catalogue-assets.tex:102",
      "project_url": "",
      "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/7fc69f53a6ca2664ef23a9597903ca6f-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "G"
      ],
      "inputs": [
        "Geometry"
      ],
      "description": "AR · Mesh tokens · Triangle meshes",
      "fields": {
        "Input": "Geometry",
        "Mechanism": "AR",
        "Representation / state": "Mesh tokens",
        "Output": "Triangle meshes",
        "Stage": "P"
      }
    },
    {
      "id": "A50",
      "name": "FullPart",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Parts and explicit mesh structure",
      "bibkey": "Ding2026FullPart",
      "title": "FullPart: Generating each 3D Part at Full Resolution",
      "year": 2026,
      "venue": "International Conference on Learning Representations",
      "authors": "Ding, Lihe and Dong, Shaocong and Li, Yaokun and Gao, Chenjian and Chen, Xiao and Han, Rui and Kuang, Yihao and Zhang, Hong and Huang, Bo and Huang, Zhanpeng and Wang, Zibin and Xu, Dan and Xue, Tianfan",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.iclr.cc/paper_files/paper/2026/hash/4c2092ec0b1370cce3fb5965ab255fae-Abstract-Conference.html",
      "doi": "",
      "arxiv": "2510.26140",
      "source": "manuscript/tables/catalogue-assets.tex:103",
      "project_url": "https://fullpart3d.github.io/",
      "url": "https://fullpart3d.github.io/",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "L"
      ],
      "inputs": [
        "Text",
        "Image",
        "Layout / graph / constraints"
      ],
      "description": "FM · Per-part grids /boxes · Textured part meshes",
      "fields": {
        "Input": "Text, Image, Layout / graph / constraints",
        "Mechanism": "FM",
        "Representation / state": "Per-part grids /boxes",
        "Output": "Textured part meshes",
        "Stage": "P/A"
      }
    },
    {
      "id": "A51",
      "name": "CubePart",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Parts and explicit mesh structure",
      "bibkey": "Zhu2026CubePart",
      "title": "CubePart: An Open-Vocabulary Part-Controllable 3D Generator",
      "year": 2026,
      "venue": "SIGGRAPH Conference Papers",
      "authors": "Zhu, Yiheng and Deng, Kangle and Fauconnier, Jean-Philippe and Navarro, Inaki and Li, Daiqing and Pun, Ava and Zhang, Yinan and Zhuang, Peiye and Sun, Xiaoxia and Agrawala, Maneesh and Bhat, Kiran and Zhou, Tinghui",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1145/3799902.3811117",
      "doi": "10.1145/3799902.3811117",
      "arxiv": "2605.28763",
      "source": "manuscript/tables/catalogue-assets.tex:105",
      "project_url": "https://cubepart.github.io/",
      "url": "https://cubepart.github.io/",
      "kind": "method",
      "input_tags": [
        "T",
        "L",
        "G"
      ],
      "inputs": [
        "Text",
        "Layout / graph / constraints",
        "Geometry"
      ],
      "description": "FM · Named-part latent sets · Named part meshes",
      "fields": {
        "Input": "Text, Layout / graph / constraints, Geometry",
        "Mechanism": "FM",
        "Representation / state": "Named-part latent sets",
        "Output": "Named part meshes",
        "Stage": "P"
      }
    },
    {
      "id": "A52",
      "name": "MeshMosaic",
      "category": "assets",
      "category_label": "Visual assets",
      "group": "Parts and explicit mesh structure",
      "bibkey": "Xu2026MeshMosaic",
      "title": "MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly",
      "year": 2026,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Xu, Rui and Xue, Tianyang and Dong, Qiujie and Wan, Le and Zhu, Zhe and Li, Peng and Dou, Zhiyang and Lin, Cheng and Xin, Shiqing and Liu, Yuan and Wang, Wenping and Komura, Taku",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2026/html/Xu_MeshMosaic_Scaling_Artist_Mesh_Generation_via_Local-to-Global_Assembly_CVPR_2026_paper.html",
      "doi": "",
      "arxiv": "2509.19995",
      "source": "manuscript/tables/catalogue-assets.tex:106",
      "project_url": "https://xrvitd.github.io/MeshMosaic/index.html",
      "url": "https://xrvitd.github.io/MeshMosaic/index.html",
      "kind": "method",
      "input_tags": [
        "G"
      ],
      "inputs": [
        "Geometry"
      ],
      "description": "AR · Local mesh sequences /boundaries · Triangle mesh",
      "fields": {
        "Input": "Geometry",
        "Mechanism": "AR",
        "Representation / state": "Local mesh sequences /boundaries",
        "Output": "Triangle mesh",
        "Stage": "P"
      }
    },
    {
      "id": "B1",
      "name": "CityEngine",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Parish2001ProceduralCities",
      "title": "Procedural modeling of cities",
      "year": 2001,
      "venue": "Proceedings of the 28th annual conference on Computer graphics and interactive techniques",
      "authors": "Yoav I. H. Parish and Pascal Müller",
      "publication_type": "venue_publication",
      "paper_url": "https://people.eecs.berkeley.edu/~sequin/CS285/PAPERS/Parish_Muller01.pdf",
      "doi": "10.1145/383259.383292",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:25",
      "project_url": "",
      "url": "https://people.eecs.berkeley.edu/~sequin/CS285/PAPERS/Parish_Muller01.pdf",
      "kind": "method",
      "input_tags": [
        "L"
      ],
      "inputs": [
        "Layout / graph / constraints"
      ],
      "description": "PROC · Road/building geometry · City meshes",
      "fields": {
        "Input": "Layout / graph / constraints",
        "Mechanism": "PROC",
        "Representation / state": "Road/building geometry",
        "Output": "City meshes",
        "Stage": "P"
      }
    },
    {
      "id": "B2",
      "name": "CGA shape",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Mueller2006ProceduralBuildings",
      "title": "Procedural modeling of buildings",
      "year": 2006,
      "venue": "ACM Transactions on Graphics",
      "authors": "Pascal Müller and Peter Wonka and Simon Haegler and Andreas Ulmer and Luc Van Gool",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1145/1141911.1141931",
      "doi": "10.1145/1141911.1141931",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:26",
      "project_url": "",
      "url": "https://doi.org/10.1145/1141911.1141931",
      "kind": "method",
      "input_tags": [
        "G",
        "L"
      ],
      "inputs": [
        "Geometry",
        "Layout / graph / constraints"
      ],
      "description": "PROC · Hierarchical shape rules · Building geometry",
      "fields": {
        "Input": "Geometry, Layout / graph / constraints",
        "Mechanism": "PROC",
        "Representation / state": "Hierarchical shape rules",
        "Output": "Building geometry",
        "Stage": "P"
      }
    },
    {
      "id": "B3",
      "name": "Residential layouts",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Merrell2010ResidentialLayouts",
      "title": "Computer-generated residential building layouts",
      "year": 2010,
      "venue": "ACM Transactions on Graphics",
      "authors": "Paul Merrell and Eric Schkufza and Vladlen Koltun",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1145/1882261.1866203",
      "doi": "10.1145/1882261.1866203",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:28",
      "project_url": "",
      "url": "https://doi.org/10.1145/1882261.1866203",
      "kind": "method",
      "input_tags": [
        "L"
      ],
      "inputs": [
        "Layout / graph / constraints"
      ],
      "description": "OPT · Architectural program/layout · Building model",
      "fields": {
        "Input": "Layout / graph / constraints",
        "Mechanism": "OPT",
        "Representation / state": "Architectural program/layout",
        "Output": "Building model",
        "Stage": "P"
      }
    },
    {
      "id": "B4",
      "name": "Example-based synthesis",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Fisher2012SceneSynthesis",
      "title": "Example-based synthesis of 3D object arrangements",
      "year": 2012,
      "venue": "ACM Transactions on Graphics",
      "authors": "Matthew Fisher and Daniel Ritchie and Manolis Savva and Thomas Funkhouser and Pat Hanrahan",
      "publication_type": "venue_publication",
      "paper_url": "https://pixl.cs.princeton.edu/pubs/Fisher_2012_ESO/",
      "doi": "10.1145/2366145.2366154",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:29",
      "project_url": "",
      "url": "https://pixl.cs.princeton.edu/pubs/Fisher_2012_ESO/",
      "kind": "method",
      "input_tags": [
        "L"
      ],
      "inputs": [
        "Layout / graph / constraints"
      ],
      "description": "PROB · Object/relationship models · Arranged scene",
      "fields": {
        "Input": "Layout / graph / constraints",
        "Mechanism": "PROB",
        "Representation / state": "Object/relationship models",
        "Output": "Arranged scene",
        "Stage": "P"
      }
    },
    {
      "id": "B5",
      "name": "DeepSynth",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Wang2018DeepScenePriors",
      "title": "Deep convolutional priors for indoor scene synthesis",
      "year": 2018,
      "venue": "ACM Transactions on Graphics",
      "authors": "Kai Wang and Manolis Savva and Angel X. Chang and Daniel Ritchie",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1145/3197517.3201362",
      "doi": "10.1145/3197517.3201362",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:31",
      "project_url": "",
      "url": "https://doi.org/10.1145/3197517.3201362",
      "kind": "method",
      "input_tags": [
        "L"
      ],
      "inputs": [
        "Layout / graph / constraints"
      ],
      "description": "SEQ · Top-down scene images · Arranged scene",
      "fields": {
        "Input": "Layout / graph / constraints",
        "Mechanism": "SEQ",
        "Representation / state": "Top-down scene images",
        "Output": "Arranged scene",
        "Stage": "P"
      }
    },
    {
      "id": "B6",
      "name": "GRAINS",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Li2019GRAINS",
      "title": "GRAINS: Generative Recursive Autoencoders for INdoor Scenes",
      "year": 2019,
      "venue": "ACM Transactions on Graphics",
      "authors": "Manyi Li and Akshay Gadi Patil and Kai Xu and Siddhartha Chaudhuri and Owais Khan and Ariel Shamir and Changhe Tu and Baoquan Chen and Daniel Cohen-Or and Hao Zhang",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1145/3303766",
      "doi": "10.1145/3303766",
      "arxiv": "1807.09193",
      "source": "manuscript/tables/catalogue-scenes.tex:32",
      "project_url": "",
      "url": "https://doi.org/10.1145/3303766",
      "kind": "method",
      "input_tags": [
        "N"
      ],
      "inputs": [
        "Latent / random seed"
      ],
      "description": "VAE · Scene hierarchy · Arranged scene",
      "fields": {
        "Input": "Latent / random seed",
        "Mechanism": "VAE",
        "Representation / state": "Scene hierarchy",
        "Output": "Arranged scene",
        "Stage": "P"
      }
    },
    {
      "id": "B7",
      "name": "ATISS",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Paschalidou2021ATISS",
      "title": "ATISS: Autoregressive Transformers for Indoor Scene Synthesis",
      "year": 2021,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Despoina Paschalidou and Amlan Kar and Maria Shugrina and Karsten Kreis and Andreas Geiger and Sanja Fidler",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper/2021/hash/64986d86a17424eeac96b08a6d519059-Abstract.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:34",
      "project_url": "",
      "url": "https://proceedings.neurips.cc/paper/2021/hash/64986d86a17424eeac96b08a6d519059-Abstract.html",
      "kind": "method",
      "input_tags": [
        "L"
      ],
      "inputs": [
        "Layout / graph / constraints"
      ],
      "description": "AR · Unordered object attributes · Layout/retrieved assets",
      "fields": {
        "Input": "Layout / graph / constraints",
        "Mechanism": "AR",
        "Representation / state": "Unordered object attributes",
        "Output": "Layout/retrieved assets",
        "Stage": "P"
      }
    },
    {
      "id": "B8",
      "name": "PlanIT",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Wang2019PlanIT",
      "title": "PlanIT: Planning and Instantiating Indoor Scenes with Relation Graph and Spatial Prior Networks",
      "year": 2019,
      "venue": "ACM Transactions on Graphics",
      "authors": "Kai Wang and Yu-An Lin and Ben Weissmann and Manolis Savva and Angel X. Chang and Daniel Ritchie",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1145/3306346.3322941",
      "doi": "10.1145/3306346.3322941",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:35",
      "project_url": "",
      "url": "https://doi.org/10.1145/3306346.3322941",
      "kind": "method",
      "input_tags": [
        "L"
      ],
      "inputs": [
        "Layout / graph / constraints"
      ],
      "description": "GRAPH+ASM · Relation graph · Arranged scene",
      "fields": {
        "Input": "Layout / graph / constraints",
        "Mechanism": "GRAPH+ASM",
        "Representation / state": "Relation graph",
        "Output": "Arranged scene",
        "Stage": "P"
      }
    },
    {
      "id": "B9",
      "name": "Graph-to-3D",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Dhamo2021GraphTo3D",
      "title": "Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs",
      "year": 2021,
      "venue": "Proceedings of the IEEE/CVF International Conference on Computer Vision",
      "authors": "Helisa Dhamo and Fabian Manhardt and Nassir Navab and Federico Tombari",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/ICCV2021/html/Dhamo_Graph-to-3D_End-to-End_Generation_and_Manipulation_of_3D_Scenes_Using_Scene_ICCV_2021_paper.html",
      "doi": "10.1109/iccv48922.2021.01604",
      "arxiv": "2108.08841",
      "source": "manuscript/tables/catalogue-scenes.tex:37",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/ICCV2021/html/Dhamo_Graph-to-3D_End-to-End_Generation_and_Manipulation_of_3D_Scenes_Using_Scene_ICCV_2021_paper.html",
      "kind": "method",
      "input_tags": [
        "L"
      ],
      "inputs": [
        "Layout / graph / constraints"
      ],
      "description": "VAE · Graph/shape/layout latents · Shapes +layout",
      "fields": {
        "Input": "Layout / graph / constraints",
        "Mechanism": "VAE",
        "Representation / state": "Graph/shape/layout latents",
        "Output": "Shapes +layout",
        "Stage": "P"
      }
    },
    {
      "id": "B10",
      "name": "EchoScene",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Zhai2024EchoScene",
      "title": "EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion",
      "year": 2024,
      "venue": "Computer Vision – ECCV",
      "authors": "Guangyao Zhai and Evin Pınar Örnek and Dave Zhenyu Chen and Ruotong Liao and Yan Di and Nassir Navab and Federico Tombari and Benjamin Busam",
      "publication_type": "venue_publication",
      "paper_url": "https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/3146_ECCV_2024_paper.php",
      "doi": "10.1007/978-3-031-72664-4_10",
      "arxiv": "2405.00915",
      "source": "manuscript/tables/catalogue-scenes.tex:38",
      "project_url": "",
      "url": "https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/3146_ECCV_2024_paper.php",
      "kind": "method",
      "input_tags": [
        "L"
      ],
      "inputs": [
        "Layout / graph / constraints"
      ],
      "description": "Diff. · Graph/shape/layout latents · Shapes +layout",
      "fields": {
        "Input": "Layout / graph / constraints",
        "Mechanism": "Diff.",
        "Representation / state": "Graph/shape/layout latents",
        "Output": "Shapes +layout",
        "Stage": "P"
      }
    },
    {
      "id": "B11",
      "name": "LayoutGPT",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Feng2023LayoutGPT",
      "title": "LayoutGPT: Compositional Visual Planning and Generation with Large Language Models",
      "year": 2023,
      "venue": "NeurIPS 2023",
      "authors": "Weixi Feng and Wanrong Zhu and Tsu-Jui Fu and Varun Jampani and Arjun Akula and Xuehai He and Sugato Basu and Xin Eric Wang and William Yang Wang",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/3a7f9e485845dac27423375c934cb4db-Abstract.html",
      "doi": "10.52202/075280-0802",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:40",
      "project_url": "",
      "url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/3a7f9e485845dac27423375c934cb4db-Abstract.html",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "LLM · Structured layout · Object boxes",
      "fields": {
        "Input": "Text",
        "Mechanism": "LLM",
        "Representation / state": "Structured layout",
        "Output": "Object boxes",
        "Stage": "P"
      }
    },
    {
      "id": "B12",
      "name": "InstructScene",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Lin2024InstructScene",
      "title": "InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior",
      "year": 2024,
      "venue": "ICLR 2024",
      "authors": "Chenguo Lin and Yadong Mu",
      "publication_type": "venue_publication",
      "paper_url": "https://chenguolin.github.io/projects/InstructScene/",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:41",
      "project_url": "",
      "url": "https://chenguolin.github.io/projects/InstructScene/",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "Diff. · Semantic-graph/layout latents · Layout/retrieved assets",
      "fields": {
        "Input": "Text",
        "Mechanism": "Diff.",
        "Representation / state": "Semantic-graph/layout latents",
        "Output": "Layout/retrieved assets",
        "Stage": "P"
      }
    },
    {
      "id": "B13",
      "name": "Holodeck",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Yang2024Holodeck",
      "title": "Holodeck: Language Guided Generation of 3D Embodied AI Environments",
      "year": 2024,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
      "authors": "Yue Yang and Fan-Yun Sun and Luca Weihs and Eli VanderBilt and Alvaro Herrasti and Winson Han and Jiajun Wu and Nick Haber and Ranjay Krishna and Lingjie Liu and Chris Callison-Burch and Mark Yatskar and Aniruddha Kembhavi and Christopher Clark",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1109/cvpr52733.2024.01536",
      "doi": "10.1109/cvpr52733.2024.01536",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:43",
      "project_url": "https://yueyang.ai/holodeck/",
      "url": "https://yueyang.ai/holodeck/",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "LLM+ASM · Objects +transforms · Simulator scene",
      "fields": {
        "Input": "Text",
        "Mechanism": "LLM+ASM",
        "Representation / state": "Objects +transforms",
        "Output": "Simulator scene",
        "Stage": "P"
      }
    },
    {
      "id": "B14",
      "name": "DiffuScene",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Tang2024DiffuScene",
      "title": "DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis",
      "year": 2024,
      "venue": "CVPR 2024",
      "authors": "Jiapeng Tang and Yinyu Nie and Lev Markhasin and Angela Dai and Justus Thies and Matthias Nießner",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Tang_DiffuScene_Denoising_Diffusion_Models_for_Generative_Indoor_Scene_Synthesis_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.01938",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:44",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Tang_DiffuScene_Denoising_Diffusion_Models_for_Generative_Indoor_Scene_Synthesis_CVPR_2024_paper.html",
      "kind": "method",
      "input_tags": [
        "T",
        "L"
      ],
      "inputs": [
        "Text",
        "Layout / graph / constraints"
      ],
      "description": "Diff. · Unordered object attributes · Layout/retrieved assets",
      "fields": {
        "Input": "Text, Layout / graph / constraints",
        "Mechanism": "Diff.",
        "Representation / state": "Unordered object attributes",
        "Output": "Layout/retrieved assets",
        "Stage": "P"
      }
    },
    {
      "id": "B15",
      "name": "PhyScene",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Yang2024PhyScene",
      "title": "PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI",
      "year": 2024,
      "venue": "CVPR 2024",
      "authors": "Yandan Yang and Baoxiong Jia and Peiyuan Zhi and Siyuan Huang",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Yang_PhyScene_Physically_Interactable_3D_Scene_Synthesis_for_Embodied_AI_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.01539",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:46",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Yang_PhyScene_Physically_Interactable_3D_Scene_Synthesis_for_Embodied_AI_CVPR_2024_paper.html",
      "kind": "method",
      "input_tags": [
        "L"
      ],
      "inputs": [
        "Layout / graph / constraints"
      ],
      "description": "Diff. · Object layouts · Arranged scene",
      "fields": {
        "Input": "Layout / graph / constraints",
        "Mechanism": "Diff.",
        "Representation / state": "Object layouts",
        "Output": "Arranged scene",
        "Stage": "P"
      }
    },
    {
      "id": "B16",
      "name": "Infinigen",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Raistrick2023Infinigen",
      "title": "Infinite Photorealistic Worlds using Procedural Generation",
      "year": 2023,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Alexander Raistrick and Lahav Lipson and Zeyu Ma and Lingjie Mei and Mingzhe Wang and Yiming Zuo and Karhan Kayan and Hongyu Wen and Beining Han and Yihan Wang and Alejandro Newell and Hei Law and Ankit Goyal and Kaiyu Yang and Jia Deng",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2023/html/Raistrick_Infinite_Photorealistic_Worlds_Using_Procedural_Generation_CVPR_2023_paper.html",
      "doi": "10.1109/cvpr52729.2023.01215",
      "arxiv": "2306.09310",
      "source": "manuscript/tables/catalogue-scenes.tex:47",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2023/html/Raistrick_Infinite_Photorealistic_Worlds_Using_Procedural_Generation_CVPR_2023_paper.html",
      "kind": "method",
      "input_tags": [
        "N"
      ],
      "inputs": [
        "Latent / random seed"
      ],
      "description": "PROC · Procedural scene graph · Mesh/material scene",
      "fields": {
        "Input": "Latent / random seed",
        "Mechanism": "PROC",
        "Representation / state": "Procedural scene graph",
        "Output": "Mesh/material scene",
        "Stage": "P"
      }
    },
    {
      "id": "B17",
      "name": "Infinigen Indoors",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Raistrick2024InfinigenIndoors",
      "title": "Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation",
      "year": 2024,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Alexander Raistrick and Lingjie Mei and Karhan Kayan and David Yan and Yiming Zuo and Beining Han and Hongyu Wen and Meenal Parakh and Stamatis Alexandropoulos and Lahav Lipson and Zeyu Ma and Jia Deng",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Raistrick_Infinigen_Indoors_Photorealistic_Indoor_Scenes_using_Procedural_Generation_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.02058",
      "arxiv": "2406.11824",
      "source": "manuscript/tables/catalogue-scenes.tex:49",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Raistrick_Infinigen_Indoors_Photorealistic_Indoor_Scenes_using_Procedural_Generation_CVPR_2024_paper.html",
      "kind": "method",
      "input_tags": [
        "L",
        "N"
      ],
      "inputs": [
        "Layout / graph / constraints",
        "Latent / random seed"
      ],
      "description": "PROC+ASM · Procedural assets/constraints · Mesh/material scene",
      "fields": {
        "Input": "Layout / graph / constraints, Latent / random seed",
        "Mechanism": "PROC+ASM",
        "Representation / state": "Procedural assets/constraints",
        "Output": "Mesh/material scene",
        "Stage": "P"
      }
    },
    {
      "id": "B18",
      "name": "SAGE",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Xia2026SAGE",
      "title": "SAGE: Scalable Agentic 3D Scene Generation for Embodied AI",
      "year": 2026,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Xia, Hongchi and Li, Xuan and Li, Zhaoshuo and Ma, Qianli and Xu, Jiashu and Liu, Ming-Yu and Cui, Yin and Lin, Tsung-Yi and Ma, Wei-Chiu and Wang, Shenlong and Song, Shuran and Wei, Fangyin",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2026/html/Xia_SAGE_Scalable_Agentic_3D_Scene_Generation_for_Embodied_AI_CVPR_2026_paper.html",
      "doi": "",
      "arxiv": "2602.10116",
      "source": "manuscript/tables/catalogue-scenes.tex:50",
      "project_url": "https://nvlabs.github.io/sage/",
      "url": "https://nvlabs.github.io/sage/",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "LLM+GEN+OPT · Objects /layout /physics attributes · Simulator scene",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "LLM+GEN+OPT",
        "Representation / state": "Objects /layout /physics attributes",
        "Output": "Simulator scene",
        "Stage": "P"
      }
    },
    {
      "id": "B19",
      "name": "Scenethesis",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Layouts and scene assembly",
      "bibkey": "Ling2026Scenethesis",
      "title": "Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation",
      "year": 2026,
      "venue": "International Conference on Learning Representations",
      "authors": "Ling, Lu and Lin, Chen-Hsuan and Lin, Tsung-Yi and Ding, Yifan and Zeng, Yu and Sheng, Yichen and Ge, Yunhao and Liu, Ming-Yu and Bera, Aniket and Li, Zhaoshuo",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.iclr.cc/paper_files/paper/2026/hash/dd172fa21119391253587a4310a1a426-Abstract-Conference.html",
      "doi": "",
      "arxiv": "2505.02836",
      "source": "manuscript/tables/catalogue-scenes.tex:52",
      "project_url": "https://research.nvidia.com/labs/dir/scenethesis/",
      "url": "https://research.nvidia.com/labs/dir/scenethesis/",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "LLM+ASM+OPT · Asset poses /geometric constraints · Assembled scene",
      "fields": {
        "Input": "Text",
        "Mechanism": "LLM+ASM+OPT",
        "Representation / state": "Asset poses /geometric constraints",
        "Output": "Assembled scene",
        "Stage": "P"
      }
    },
    {
      "id": "B20",
      "name": "Ctrl-Room",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Reconstruction and incremental geometry",
      "bibkey": "Fang2025CtrlRoom",
      "title": "Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints",
      "year": 2025,
      "venue": "International Conference on 3D Vision",
      "authors": "Chuan Fang and Yuan Dong and Kunming Luo and Xiaotao Hu and Rakesh Shrestha and Ping Tan",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1109/3DV66043.2025.00069",
      "doi": "10.1109/3DV66043.2025.00069",
      "arxiv": "2310.03602",
      "source": "manuscript/tables/catalogue-scenes.tex:54",
      "project_url": "",
      "url": "https://doi.org/10.1109/3DV66043.2025.00069",
      "kind": "method",
      "input_tags": [
        "T",
        "L"
      ],
      "inputs": [
        "Text",
        "Layout / graph / constraints"
      ],
      "description": "Diff.+REC · Layout/panorama/mesh · Room mesh",
      "fields": {
        "Input": "Text, Layout / graph / constraints",
        "Mechanism": "Diff.+REC",
        "Representation / state": "Layout/panorama/mesh",
        "Output": "Room mesh",
        "Stage": "P"
      }
    },
    {
      "id": "B21",
      "name": "Text2Room",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Reconstruction and incremental geometry",
      "bibkey": "Hollein2023Text2Room",
      "title": "Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models",
      "year": 2023,
      "venue": "Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)",
      "authors": "Lukas Höllein and Ang Cao and Andrew Owens and Justin Johnson and Matthias Nießner",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1109/iccv51070.2023.00727",
      "doi": "10.1109/iccv51070.2023.00727",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:56",
      "project_url": "https://lukashoel.github.io/text-to-room/",
      "url": "https://lukashoel.github.io/text-to-room/",
      "kind": "method",
      "input_tags": [
        "T",
        "P"
      ],
      "inputs": [
        "Text",
        "Camera / pose"
      ],
      "description": "INP+REC · Retained textured mesh · Textured mesh",
      "fields": {
        "Input": "Text, Camera / pose",
        "Mechanism": "INP+REC",
        "Representation / state": "Retained textured mesh",
        "Output": "Textured mesh",
        "Stage": "P"
      }
    },
    {
      "id": "B22",
      "name": "SceneScape",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Reconstruction and incremental geometry",
      "bibkey": "Fridman2023SceneScape",
      "title": "SceneScape: Text-Driven Consistent Scene Generation",
      "year": 2023,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Rafail Fridman and Amit Abecasis and Yoni Kasten and Tali Dekel",
      "publication_type": "venue_publication",
      "paper_url": "https://papers.neurips.cc/paper_files/paper/2023/hash/7d62a85ebfed2f680eb5544beae93191-Abstract-Conference.html",
      "doi": "10.52202/075280-1734",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:57",
      "project_url": "https://scenescape.github.io/",
      "url": "https://scenescape.github.io/",
      "kind": "method",
      "input_tags": [
        "T",
        "P"
      ],
      "inputs": [
        "Text",
        "Camera / pose"
      ],
      "description": "INP+REC · Retained textured mesh · Mesh/views",
      "fields": {
        "Input": "Text, Camera / pose",
        "Mechanism": "INP+REC",
        "Representation / state": "Retained textured mesh",
        "Output": "Mesh/views",
        "Stage": "P"
      }
    },
    {
      "id": "B23",
      "name": "HunyuanWorld 1.0",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Reconstruction and incremental geometry",
      "bibkey": "HunyuanWorldTeam2025HunyuanWorld",
      "title": "HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels",
      "year": 2025,
      "venue": "arXiv",
      "authors": "HunyuanWorld Team and Zhenwei Wang and Yuhao Liu and Junta Wu and Zixiao Gu and Haoyuan Wang and Xuhui Zuo and Tianyu Huang and Wenhuan Li and Sheng Zhang and Yihang Lian and Yulin Tsai and Lifu Wang and Sicong Liu and Puhua Jiang and Xianghui Yang and Dongyuan Guo and Yixuan Tang and Xinyue Mao and Jiaao Yu and Junlin Yu and Jihong Zhang and Meng Chen and Liang Dong and Yiwen Jia and Chao Zhang and Yonghao Tan and Hao Zhang and Zheng Ye and Peng He and Runzhou Wu and Minghui Chen and Zhan Li and Wangchen Qin and Lei Wang and Yifu Sun and Lin Niu and Xiang Yuan and Xiaofeng Yang and Yingping He and Jie Xiao and Yangyu Tao and Jianchen Zhu and Jinbao Xue and Kai Liu and Chongqing Zhao and Xinming Wu and Tian Liu and Peng Chen and Di Wang and Yuhong Liu and Linus and Jie Jiang and Tengfei Wang and Chunchao Guo",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2507.21809v1",
      "doi": "10.48550/arXiv.2507.21809",
      "arxiv": "2507.21809",
      "source": "manuscript/tables/catalogue-scenes.tex:59",
      "project_url": "https://3d-models.hunyuan.tencent.com/world/?currentTab=HunyuanWorld-1.0&lang=en",
      "url": "https://3d-models.hunyuan.tencent.com/world/?currentTab=HunyuanWorld-1.0&lang=en",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "GEN+REC · Layered panorama/meshes · Object-level meshes",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "GEN+REC",
        "Representation / state": "Layered panorama/meshes",
        "Output": "Object-level meshes",
        "Stage": "P"
      }
    },
    {
      "id": "B24",
      "name": "LucidDreamer",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Reconstruction and incremental geometry",
      "bibkey": "Chung2025LucidDreamerScenes",
      "title": "LucidDreamer: Domain-Free Generation of 3D Gaussian Splatting Scenes",
      "year": 2025,
      "venue": "IEEE Transactions on Visualization and Computer Graphics",
      "authors": "Jaeyoung Chung and Suyoung Lee and Hyeongjin Nam and Jaerin Lee and Kyoung Mu Lee",
      "publication_type": "venue_publication",
      "paper_url": "https://luciddreamer-cvlab.github.io/",
      "doi": "10.1109/TVCG.2025.3611489",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:60",
      "project_url": "",
      "url": "https://luciddreamer-cvlab.github.io/",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "P"
      ],
      "inputs": [
        "Text",
        "Image",
        "Camera / pose"
      ],
      "description": "Diff.+OPT · Point-cloud/Gaussians · Gaussian scene",
      "fields": {
        "Input": "Text, Image, Camera / pose",
        "Mechanism": "Diff.+OPT",
        "Representation / state": "Point-cloud/Gaussians",
        "Output": "Gaussian scene",
        "Stage": "P"
      }
    },
    {
      "id": "B25",
      "name": "WonderJourney",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Reconstruction and incremental geometry",
      "bibkey": "Yu2024WonderJourney",
      "title": "WonderJourney: Going from Anywhere to Everywhere",
      "year": 2024,
      "venue": "CVPR 2024",
      "authors": "Hong-Xing Yu and Haoyi Duan and Junhwa Hur and Kyle Sargent and Michael Rubinstein and William T. Freeman and Forrester Cole and Deqing Sun and Noah Snavely and Jiajun Wu and Charles Herrmann",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Yu_WonderJourney_Going_from_Anywhere_to_Everywhere_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.00636",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:62",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Yu_WonderJourney_Going_from_Anywhere_to_Everywhere_CVPR_2024_paper.html",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "LLM+GEN · Connected point-cloud scenes · Scene journey",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "LLM+GEN",
        "Representation / state": "Connected point-cloud scenes",
        "Output": "Scene journey",
        "Stage": "P"
      }
    },
    {
      "id": "B26",
      "name": "WonderWorld",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Reconstruction and incremental geometry",
      "bibkey": "Yu2025WonderWorld",
      "title": "WonderWorld: Interactive 3D Scene Generation from a Single Image",
      "year": 2025,
      "venue": "CVPR 2025",
      "authors": "Hong-Xing Yu and Haoyi Duan and Charles Herrmann and William T. Freeman and Jiajun Wu",
      "publication_type": "venue_publication",
      "paper_url": "https://kovenyu.com/wonderworld/",
      "doi": "10.1109/cvpr52734.2025.00555",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:63",
      "project_url": "",
      "url": "https://kovenyu.com/wonderworld/",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "P"
      ],
      "inputs": [
        "Text",
        "Image",
        "Camera / pose"
      ],
      "description": "Diff. · Layered Gaussian surfels · Gaussian scene",
      "fields": {
        "Input": "Text, Image, Camera / pose",
        "Mechanism": "Diff.",
        "Representation / state": "Layered Gaussian surfels",
        "Output": "Gaussian scene",
        "Stage": "A"
      }
    },
    {
      "id": "B27",
      "name": "Invisible Stitch",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Reconstruction and incremental geometry",
      "bibkey": "Engstler2025InvisibleStitch",
      "title": "Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting",
      "year": 2025,
      "venue": "International Conference on 3D Vision (3DV) 2025",
      "authors": "Paul Engstler and Andrea Vedaldi and Iro Laina and Christian Rupprecht",
      "publication_type": "venue_publication",
      "paper_url": "https://robots.ox.ac.uk/~vgg/publications/2025/Engstler25/",
      "doi": "10.1109/3DV66043.2025.00047",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:65",
      "project_url": "",
      "url": "https://robots.ox.ac.uk/~vgg/publications/2025/Engstler25/",
      "kind": "method",
      "input_tags": [
        "I",
        "P"
      ],
      "inputs": [
        "Image",
        "Camera / pose"
      ],
      "description": "INP+OPT · Point-cloud/Gaussians · Gaussian scene",
      "fields": {
        "Input": "Image, Camera / pose",
        "Mechanism": "INP+OPT",
        "Representation / state": "Point-cloud/Gaussians",
        "Output": "Gaussian scene",
        "Stage": "P"
      }
    },
    {
      "id": "B28",
      "name": "Text2NeRF",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Reconstruction and incremental geometry",
      "bibkey": "Zhang2024Text2NeRF",
      "title": "Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields",
      "year": 2024,
      "venue": "IEEE Transactions on Visualization and Computer Graphics",
      "authors": "Jingbo Zhang and Xiaoyu Li and Ziyu Wan and Can Wang and Jing Liao",
      "publication_type": "venue_publication",
      "paper_url": "https://scholars.cityu.edu.hk/en/publications/text2nerf-text-driven-3d-scene-generation-with-neural-radiance-fi/",
      "doi": "10.1109/TVCG.2024.3361502",
      "arxiv": "2305.11588",
      "source": "manuscript/tables/catalogue-scenes.tex:66",
      "project_url": "",
      "url": "https://scholars.cityu.edu.hk/en/publications/text2nerf-text-driven-3d-scene-generation-with-neural-radiance-fi/",
      "kind": "method",
      "input_tags": [
        "T",
        "P"
      ],
      "inputs": [
        "Text",
        "Camera / pose"
      ],
      "description": "INP+OPT · Radiance field · NeRF scene",
      "fields": {
        "Input": "Text, Camera / pose",
        "Mechanism": "INP+OPT",
        "Representation / state": "Radiance field",
        "Output": "NeRF scene",
        "Stage": "P"
      }
    },
    {
      "id": "B29",
      "name": "DreamScene360",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Reconstruction and incremental geometry",
      "bibkey": "Zhou2024DreamScene360",
      "title": "DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting",
      "year": 2024,
      "venue": "ECCV 2024",
      "authors": "Shijie Zhou and Zhiwen Fan and Dejia Xu and Haoran Chang and Pradyumna Chari and Tejas Bharadwaj and Suya You and Zhangyang Wang and Achuta Kadambi",
      "publication_type": "venue_publication",
      "paper_url": "https://dreamscene360.github.io/",
      "doi": "10.1007/978-3-031-72658-3_19",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:68",
      "project_url": "",
      "url": "https://dreamscene360.github.io/",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "GEN+REC · Point-cloud/Gaussians · Gaussian scene",
      "fields": {
        "Input": "Text",
        "Mechanism": "GEN+REC",
        "Representation / state": "Point-cloud/Gaussians",
        "Output": "Gaussian scene",
        "Stage": "P"
      }
    },
    {
      "id": "B30",
      "name": "Pano3DComposer",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Reconstruction and incremental geometry",
      "bibkey": "Qiu2026Pano3DComposer",
      "title": "Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image",
      "year": 2026,
      "venue": "CVPR 2026",
      "authors": "Zidian Qiu and Ancong Wu",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2026/html/Qiu_Pano3DComposer_Feed-Forward_Compositional_3D_Scene_Generation_from_Single_Panoramic_Image_CVPR_2026_paper.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:69",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2026/html/Qiu_Pano3DComposer_Feed-Forward_Compositional_3D_Scene_Generation_from_Single_Panoramic_Image_CVPR_2026_paper.html",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "GEN+ALIGN · Objects +transforms · Compositional 3D scene",
      "fields": {
        "Input": "Image",
        "Mechanism": "GEN+ALIGN",
        "Representation / state": "Objects +transforms",
        "Output": "Compositional 3D scene",
        "Stage": "P"
      }
    },
    {
      "id": "B31",
      "name": "I-Scene",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Reconstruction and incremental geometry",
      "bibkey": "Ling2026IScene",
      "title": "I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners",
      "year": 2026,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Ling, Lu and Ge, Yunhao and Sheng, Yichen and Bera, Aniket",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2026/html/Ling_I-Scene_3D_Instance_Models_are_Implicit_Generalizable_Spatial_Learners_CVPR_2026_paper.html",
      "doi": "",
      "arxiv": "2512.13683",
      "source": "manuscript/tables/catalogue-scenes.tex:71",
      "project_url": "https://luling06.github.io/I-Scene-project/",
      "url": "https://luling06.github.io/I-Scene-project/",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "RF · Instance latents /scene context · Object-separated scene",
      "fields": {
        "Input": "Image",
        "Mechanism": "RF",
        "Representation / state": "Instance latents /scene context",
        "Output": "Object-separated scene",
        "Stage": "P"
      }
    },
    {
      "id": "B32",
      "name": "SceneDreamer",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Scene fields, views, and panoramas",
      "bibkey": "Chen2023SceneDreamer",
      "title": "SceneDreamer: Unbounded 3D Scene Generation From 2D Image Collections",
      "year": 2023,
      "venue": "IEEE Transactions on Pattern Analysis and Machine Intelligence",
      "authors": "Zhaoxi Chen and Guangcong Wang and Ziwei Liu",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1109/TPAMI.2023.3321857",
      "doi": "10.1109/TPAMI.2023.3321857",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:73",
      "project_url": "https://scene-dreamer.github.io/",
      "url": "https://scene-dreamer.github.io/",
      "kind": "method",
      "input_tags": [
        "N"
      ],
      "inputs": [
        "Latent / random seed"
      ],
      "description": "GAN · BEV/generative hash-grid · Rendered views",
      "fields": {
        "Input": "Latent / random seed",
        "Mechanism": "GAN",
        "Representation / state": "BEV/generative hash-grid",
        "Output": "Rendered views",
        "Stage": "P"
      }
    },
    {
      "id": "B33",
      "name": "MVDiffusion",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Scene fields, views, and panoramas",
      "bibkey": "Tang2023MVDiffusion",
      "title": "MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion",
      "year": 2023,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Tang, Shitao and Zhang, Fuyang and Chen, Jiacheng and Wang, Peng and Furukawa, Yasutaka",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.nips.cc/paper_files/paper/2023/hash/a0da690a47b2f52faa63f6fe054057b5-Abstract-Conference.html",
      "doi": "10.52202/075280-2229",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:75",
      "project_url": "",
      "url": "https://proceedings.nips.cc/paper_files/paper/2023/hash/a0da690a47b2f52faa63f6fe054057b5-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "T",
        "G",
        "P"
      ],
      "inputs": [
        "Text",
        "Geometry",
        "Camera / pose"
      ],
      "description": "Diff. · Multiview image latents · Panorama/multiview images",
      "fields": {
        "Input": "Text, Geometry, Camera / pose",
        "Mechanism": "Diff.",
        "Representation / state": "Multiview image latents",
        "Output": "Panorama/multiview images",
        "Stage": "P"
      }
    },
    {
      "id": "B34",
      "name": "PanFusion",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Scene fields, views, and panoramas",
      "bibkey": "Zhang2024PanFusion",
      "title": "Taming Stable Diffusion for Text to 360° Panorama Image Generation",
      "year": 2024,
      "venue": "CVPR 2024",
      "authors": "Cheng Zhang and Qianyi Wu and Camilo Cruz Gambardella and Xiaoshui Huang and Dinh Phung and Wanli Ouyang and Jianfei Cai",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Zhang_Taming_Stable_Diffusion_for_Text_to_360_Panorama_Image_Generation_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.00607",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:76",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Zhang_Taming_Stable_Diffusion_for_Text_to_360_Panorama_Image_Generation_CVPR_2024_paper.html",
      "kind": "method",
      "input_tags": [
        "T",
        "L"
      ],
      "inputs": [
        "Text",
        "Layout / graph / constraints"
      ],
      "description": "Diff. · Panorama/perspective latents · Panoramic image",
      "fields": {
        "Input": "Text, Layout / graph / constraints",
        "Mechanism": "Diff.",
        "Representation / state": "Panorama/perspective latents",
        "Output": "Panoramic image",
        "Stage": "P"
      }
    },
    {
      "id": "B35",
      "name": "SceneCraft",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Scene fields, views, and panoramas",
      "bibkey": "Yang2024SceneCraft",
      "title": "SceneCraft: Layout-Guided 3D Scene Generation",
      "year": 2024,
      "venue": "NeurIPS 2024",
      "authors": "Xiuyu Yang and Yunze Man and Jun-Kun Chen and Yu-Xiong Wang",
      "publication_type": "venue_publication",
      "paper_url": "https://orangesodahub.github.io/SceneCraft/",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:78",
      "project_url": "",
      "url": "https://orangesodahub.github.io/SceneCraft/",
      "kind": "method",
      "input_tags": [
        "T",
        "L"
      ],
      "inputs": [
        "Text",
        "Layout / graph / constraints"
      ],
      "description": "Diff.+REC · Semantic/depth proxies/NeRF · NeRF scene",
      "fields": {
        "Input": "Text, Layout / graph / constraints",
        "Mechanism": "Diff.+REC",
        "Representation / state": "Semantic/depth proxies/NeRF",
        "Output": "NeRF scene",
        "Stage": "P"
      }
    },
    {
      "id": "B36",
      "name": "360DVD",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Scene fields, views, and panoramas",
      "bibkey": "Wang2024ThreeSixtyDVD",
      "title": "360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model",
      "year": 2024,
      "venue": "CVPR 2024",
      "authors": "Qian Wang and Weiqi Li and Chong Mou and Xinhua Cheng and Jian Zhang",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Wang_360DVD_Controllable_Panorama_Video_Generation_with_360-Degree_Video_Diffusion_Model_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.00660",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:79",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Wang_360DVD_Controllable_Panorama_Video_Generation_with_360-Degree_Video_Diffusion_Model_CVPR_2024_paper.html",
      "kind": "method",
      "input_tags": [
        "T",
        "M"
      ],
      "inputs": [
        "Text",
        "Motion / flow"
      ],
      "description": "Diff. · Panoramic video latents · Panoramic video",
      "fields": {
        "Input": "Text, Motion / flow",
        "Mechanism": "Diff.",
        "Representation / state": "Panoramic video latents",
        "Output": "Panoramic video",
        "Stage": "P"
      }
    },
    {
      "id": "B37",
      "name": "CubeComposer",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Scene fields, views, and panoramas",
      "bibkey": "Li2026CubeComposer",
      "title": "CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video",
      "year": 2026,
      "venue": "CVPR 2026",
      "authors": "Lingen Li and Guangzhi Wang and Xiaoyu Li and Zhaoyang Zhang and Qi Dou and Jinwei Gu and Tianfan Xue and Ying Shan",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2026/html/Li_CubeComposer_Spatio-Temporal_Autoregressive_4K_360deg_Video_Generation_from_Perspective_Video_CVPR_2026_paper.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:81",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2026/html/Li_CubeComposer_Spatio-Temporal_Autoregressive_4K_360deg_Video_Generation_from_Perspective_Video_CVPR_2026_paper.html",
      "kind": "method",
      "input_tags": [
        "V"
      ],
      "inputs": [
        "Video"
      ],
      "description": "AR · Cube-face video latents · Panoramic video",
      "fields": {
        "Input": "Video",
        "Mechanism": "AR",
        "Representation / state": "Cube-face video latents",
        "Output": "Panoramic video",
        "Stage": "P"
      }
    },
    {
      "id": "B38",
      "name": "SynCity",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Spatial expansion, control, and memory",
      "bibkey": "Engstler2025SynCity",
      "title": "SynCity: Training-Free Generation of 3D Worlds",
      "year": 2025,
      "venue": "Proceedings of the IEEE/CVF International Conference on Computer Vision",
      "authors": "Paul Engstler and Aleksandar Shtedritski and Iro Laina and Christian Rupprecht and Andrea Vedaldi",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/ICCV2025/html/Engstler_SynCity_Training-Free_Generation_of_3D_Worlds_ICCV_2025_paper.html",
      "doi": "10.1109/iccv51701.2025.02561",
      "arxiv": "2503.16420",
      "source": "manuscript/tables/catalogue-scenes.tex:83",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/ICCV2025/html/Engstler_SynCity_Training-Free_Generation_of_3D_Worlds_ICCV_2025_paper.html",
      "kind": "method",
      "input_tags": [
        "T",
        "L"
      ],
      "inputs": [
        "Text",
        "Layout / graph / constraints"
      ],
      "description": "GEN · Structured latents/Gaussians · Gaussian world",
      "fields": {
        "Input": "Text, Layout / graph / constraints",
        "Mechanism": "GEN",
        "Representation / state": "Structured latents/Gaussians",
        "Output": "Gaussian world",
        "Stage": "P"
      }
    },
    {
      "id": "B39",
      "name": "Voyager",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Spatial expansion, control, and memory",
      "bibkey": "Huang2025Voyager",
      "title": "Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation",
      "year": 2025,
      "venue": "ACM Transactions on Graphics",
      "authors": "Tianyu Huang and Wangguandong Zheng and Tengfei Wang and Yuhao Liu and Zhenwei Wang and Junta Wu and Jie Jiang and Hui Li and Rynson W. H. Lau and Wangmeng Zuo and Chunchao Guo",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1145/3763330",
      "doi": "10.1145/3763330",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:85",
      "project_url": "https://3d-models.hunyuan.tencent.com/world/?currentTab=HunyuanWorld-Voyager&lang=en",
      "url": "https://3d-models.hunyuan.tencent.com/world/?currentTab=HunyuanWorld-Voyager&lang=en",
      "kind": "method",
      "input_tags": [
        "I",
        "P"
      ],
      "inputs": [
        "Image",
        "Camera / pose"
      ],
      "description": "Diff. · Colored point-cloud cache · RGB-D video",
      "fields": {
        "Input": "Image, Camera / pose",
        "Mechanism": "Diff.",
        "Representation / state": "Colored point-cloud cache",
        "Output": "RGB-D video",
        "Stage": "P"
      }
    },
    {
      "id": "B40",
      "name": "HY-World 2.0",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Spatial expansion, control, and memory",
      "bibkey": "HYWorldTeam2026HYWorld2",
      "title": "HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds",
      "year": 2026,
      "venue": "arXiv",
      "authors": "Team HY-World and Chenjie Cao and Xuhui Zuo and Zhenwei Wang and Yisu Zhang and Junta Wu and Zhenyang Liu and Yuning Gong and Yang Liu and Bo Yuan and Chao Zhang and Coopers Li and Dongyuan Guo and Fan Yang and Haiyu Zhang and Hang Cao and Jianchen Zhu and Jiaxin Lin and Jie Xiao and Jihong Zhang and Junlin Yu and Lei Wang and Lifu Wang and Lilin Wang and Linus and Minghui Chen and Peng He and Penghao Zhao and Qi Chen and Rui Chen and Rui Shao and Sicong Liu and Wangchen Qin and Xiaochuan Niu and Xiang Yuan and Yi Sun and Yifei Tang and Yifu Sun and Yihang Lian and Yonghao Tan and Yuhong Liu and Yuyang Yin and Zhiyuan Min and Tengfei Wang and Chunchao Guo",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2604.14268v1",
      "doi": "10.48550/arXiv.2604.14268",
      "arxiv": "2604.14268",
      "source": "manuscript/tables/catalogue-scenes.tex:86",
      "project_url": "https://3d-models.hunyuan.tencent.com/world/?currentTab=HYWorld-2.0&lang=en",
      "url": "https://3d-models.hunyuan.tencent.com/world/?currentTab=HYWorld-2.0&lang=en",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "V",
        "P"
      ],
      "inputs": [
        "Text",
        "Image",
        "Video",
        "Camera / pose"
      ],
      "description": "GEN+REC · Point-cloud/keyframes/Gaussians · Gaussians/collision mesh",
      "fields": {
        "Input": "Text, Image, Video, Camera / pose",
        "Mechanism": "GEN+REC",
        "Representation / state": "Point-cloud/keyframes/Gaussians",
        "Output": "Gaussians/collision mesh",
        "Stage": "P"
      }
    },
    {
      "id": "B41",
      "name": "SEVA",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Spatial expansion, control, and memory",
      "bibkey": "Zhou2025SEVA",
      "title": "Stable Virtual Camera: Generative View Synthesis with Diffusion Models",
      "year": 2025,
      "venue": "ICCV 2025",
      "authors": "Jensen Zhou and Hang Gao and Vikram Voleti and Aaryaman Vasishta and Chun-Han Yao and Mark Boss and Philip Torr and Christian Rupprecht and Varun Jampani",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/ICCV2025/html/Zhou_Stable_Virtual_Camera_Generative_View_Synthesis_with_Diffusion_Models_ICCV_2025_paper.html",
      "doi": "10.1109/ICCV51701.2025.01153",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:88",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/ICCV2025/html/Zhou_Stable_Virtual_Camera_Generative_View_Synthesis_with_Diffusion_Models_ICCV_2025_paper.html",
      "kind": "method",
      "input_tags": [
        "I",
        "P"
      ],
      "inputs": [
        "Image",
        "Camera / pose"
      ],
      "description": "Diff. · Multiview image latents · Novel-view images",
      "fields": {
        "Input": "Image, Camera / pose",
        "Mechanism": "Diff.",
        "Representation / state": "Multiview image latents",
        "Output": "Novel-view images",
        "Stage": "P"
      }
    },
    {
      "id": "B42",
      "name": "ViewCrafter",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Spatial expansion, control, and memory",
      "bibkey": "Yu2025ViewCrafter",
      "title": "ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis",
      "year": 2025,
      "venue": "IEEE Transactions on Pattern Analysis and Machine Intelligence",
      "authors": "Wangbo Yu and Jinbo Xing and Li Yuan and Wenbo Hu and Xiaoyu Li and Zhipeng Huang and Xiangjun Gao and Tien-Tsin Wong and Ying Shan and Yonghong Tian",
      "publication_type": "venue_publication",
      "paper_url": "https://drexubery.github.io/ViewCrafter/",
      "doi": "10.1109/TPAMI.2025.3613256",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:89",
      "project_url": "",
      "url": "https://drexubery.github.io/ViewCrafter/",
      "kind": "method",
      "input_tags": [
        "I",
        "P"
      ],
      "inputs": [
        "Image",
        "Camera / pose"
      ],
      "description": "Diff. · Point-cloud guidance · Novel-view video",
      "fields": {
        "Input": "Image, Camera / pose",
        "Mechanism": "Diff.",
        "Representation / state": "Point-cloud guidance",
        "Output": "Novel-view video",
        "Stage": "P"
      }
    },
    {
      "id": "B43",
      "name": "See3D",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Spatial expansion, control, and memory",
      "bibkey": "Ma2025See3D",
      "title": "You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale",
      "year": 2025,
      "venue": "CVPR 2025",
      "authors": "Baorui Ma and Huachen Gao and Haoge Deng and Zhengxiong Luo and Tiejun Huang and Lulu Tang and Xinlong Wang",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2412.06699",
      "doi": "10.1109/cvpr52734.2025.00194",
      "arxiv": "2412.06699",
      "source": "manuscript/tables/catalogue-scenes.tex:91",
      "project_url": "",
      "url": "https://arxiv.org/abs/2412.06699",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "Diff. · Visual-condition latents · Multiview images",
      "fields": {
        "Input": "Image",
        "Mechanism": "Diff.",
        "Representation / state": "Visual-condition latents",
        "Output": "Multiview images",
        "Stage": "P"
      }
    },
    {
      "id": "B44",
      "name": "FlexWorld",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Spatial expansion, control, and memory",
      "bibkey": "Chen2025FlexWorld",
      "title": "FlexWorld: Progressively Expanding 3D Scenes for Flexible-View Exploration",
      "year": 2025,
      "venue": "NeurIPS 2025",
      "authors": "Luxi Chen and Zihan Zhou and Min Zhao and Yikai Wang and Ge Zhang and Wenhao Huang and Hao Sun and Ji-Rong Wen and Chongxuan Li",
      "publication_type": "venue_publication",
      "paper_url": "https://papers.neurips.cc/paper_files/paper/2025/hash/fb23e1cbc747c96c07c7a1681b567c35-Abstract-Conference.html",
      "doi": "10.52202/085713-5732",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:92",
      "project_url": "",
      "url": "https://papers.neurips.cc/paper_files/paper/2025/hash/fb23e1cbc747c96c07c7a1681b567c35-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "I",
        "P"
      ],
      "inputs": [
        "Image",
        "Camera / pose"
      ],
      "description": "Diff.+REC · Persistent Gaussian scene · Gaussian scene/video",
      "fields": {
        "Input": "Image, Camera / pose",
        "Mechanism": "Diff.+REC",
        "Representation / state": "Persistent Gaussian scene",
        "Output": "Gaussian scene/video",
        "Stage": "P"
      }
    },
    {
      "id": "B45",
      "name": "GEN3C",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Spatial expansion, control, and memory",
      "bibkey": "Ren2025GEN3C",
      "title": "GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control",
      "year": 2025,
      "venue": "CVPR 2025",
      "authors": "Xuanchi Ren and Tianchang Shen and Jiahui Huang and Huan Ling and Yifan Lu and Merlin Nimier-David and Thomas Müller and Alexander Keller and Sanja Fidler and Jun Gao",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2025/html/Ren_GEN3C_3D-Informed_World-Consistent_Video_Generation_with_Precise_Camera_Control_CVPR_2025_paper.html",
      "doi": "10.1109/cvpr52734.2025.00574",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:94",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2025/html/Ren_GEN3C_3D-Informed_World-Consistent_Video_Generation_with_Precise_Camera_Control_CVPR_2025_paper.html",
      "kind": "method",
      "input_tags": [
        "I",
        "V",
        "P"
      ],
      "inputs": [
        "Image",
        "Video",
        "Camera / pose"
      ],
      "description": "Diff. · 3D point-cloud cache · Camera-controlled video",
      "fields": {
        "Input": "Image, Video, Camera / pose",
        "Mechanism": "Diff.",
        "Representation / state": "3D point-cloud cache",
        "Output": "Camera-controlled video",
        "Stage": "P"
      }
    },
    {
      "id": "B46",
      "name": "SceneFrom3D",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Spatial expansion, control, and memory",
      "bibkey": "Kim2026SceneFrom3D",
      "title": "SceneFrom3D: Geometry-Conditioned Outdoor 3D Scene Generation via View Scheduling with Object-Level Control",
      "year": 2026,
      "venue": "arXiv",
      "authors": "Kim, Geonung and Park, Jeongeun and Ryu, Nuri and Liu, Di and Cho, Sunghyun",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2607.04540",
      "doi": "10.48550/arXiv.2607.04540",
      "arxiv": "2607.04540",
      "source": "manuscript/tables/catalogue-scenes.tex:95",
      "project_url": "https://kimgeonung.github.io/SceneFrom3D/",
      "url": "https://kimgeonung.github.io/SceneFrom3D/",
      "kind": "method",
      "input_tags": [
        "G",
        "I"
      ],
      "inputs": [
        "Geometry",
        "Image"
      ],
      "description": "Diff.+REC · Geometry /scheduled views /GS · Gaussian scene",
      "fields": {
        "Input": "Geometry, Image",
        "Mechanism": "Diff.+REC",
        "Representation / state": "Geometry /scheduled views /GS",
        "Output": "Gaussian scene",
        "Stage": "P"
      }
    },
    {
      "id": "B47",
      "name": "Instruct-NeRF2NeRF",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Scene editing",
      "bibkey": "Haque2023InstructNeRF2NeRF",
      "title": "Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions",
      "year": 2023,
      "venue": "ICCV 2023",
      "authors": "Ayaan Haque and Matthew Tancik and Alexei A. Efros and Aleksander Holynski and Angjoo Kanazawa",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/ICCV2023/html/Haque_Instruct-NeRF2NeRF_Editing_3D_Scenes_with_Instructions_ICCV_2023_paper.html",
      "doi": "10.1109/iccv51070.2023.01808",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:98",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/ICCV2023/html/Haque_Instruct-NeRF2NeRF_Editing_3D_Scenes_with_Instructions_ICCV_2023_paper.html",
      "kind": "method",
      "input_tags": [
        "T",
        "G"
      ],
      "inputs": [
        "Text",
        "Geometry"
      ],
      "description": "EDIT+OPT · Radiance field · Edited NeRF",
      "fields": {
        "Input": "Text, Geometry",
        "Mechanism": "EDIT+OPT",
        "Representation / state": "Radiance field",
        "Output": "Edited NeRF",
        "Stage": "P"
      }
    },
    {
      "id": "B48",
      "name": "GaussianEditor",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Scene editing",
      "bibkey": "Chen2024GaussianEditor",
      "title": "GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting",
      "year": 2024,
      "venue": "CVPR 2024",
      "authors": "Yiwen Chen and Zilong Chen and Chi Zhang and Feng Wang and Xiaofeng Yang and Yikai Wang and Zhongang Cai and Lei Yang and Huaping Liu and Guosheng Lin",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Chen_GaussianEditor_Swift_and_Controllable_3D_Editing_with_Gaussian_Splatting_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.02029",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:99",
      "project_url": "https://buaacyw.github.io/gaussian-editor/",
      "url": "https://buaacyw.github.io/gaussian-editor/",
      "kind": "method",
      "input_tags": [
        "T",
        "G"
      ],
      "inputs": [
        "Text",
        "Geometry"
      ],
      "description": "Diff.+EDIT · Semantic Gaussian scene · Edited Gaussians",
      "fields": {
        "Input": "Text, Geometry",
        "Mechanism": "Diff.+EDIT",
        "Representation / state": "Semantic Gaussian scene",
        "Output": "Edited Gaussians",
        "Stage": "A"
      }
    },
    {
      "id": "B49",
      "name": "SceneFactor",
      "category": "scenes",
      "category_label": "Spatial scenes",
      "group": "Scene editing",
      "bibkey": "Bokhovkin2025SceneFactor",
      "title": "SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation",
      "year": 2025,
      "venue": "CVPR 2025",
      "authors": "Aleksey Bokhovkin and Quan Meng and Shubham Tulsiani and Angela Dai",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2025/html/Bokhovkin_SceneFactor_Factored_Latent_3D_Diffusion_for_Controllable_3D_Scene_Generation_CVPR_2025_paper.html",
      "doi": "10.1109/cvpr52734.2025.00067",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-scenes.tex:101",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2025/html/Bokhovkin_SceneFactor_Factored_Latent_3D_Diffusion_for_Controllable_3D_Scene_Generation_CVPR_2025_paper.html",
      "kind": "method",
      "input_tags": [
        "T",
        "L"
      ],
      "inputs": [
        "Text",
        "Layout / graph / constraints"
      ],
      "description": "Diff. · Semantic/geometric latents · 3D scene",
      "fields": {
        "Input": "Text, Layout / graph / constraints",
        "Mechanism": "Diff.",
        "Representation / state": "Semantic/geometric latents",
        "Output": "3D scene",
        "Stage": "P"
      }
    },
    {
      "id": "C1",
      "name": "Video Diffusion",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Ho2022VideoDiffusion",
      "title": "Video Diffusion Models",
      "year": 2022,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Ho, Jonathan and Salimans, Tim and Gritsenko, Alexey and Chan, William and Norouzi, Mohammad and Fleet, David J.",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper_files/paper/2022/hash/39235c56aef13fb05a6adc95eb9d8d66-Abstract-Conference.html",
      "doi": "10.52202/068431-0628",
      "arxiv": "2204.03458",
      "source": "manuscript/tables/catalogue-temporal.tex:25",
      "project_url": "",
      "url": "https://proceedings.neurips.cc/paper_files/paper/2022/hash/39235c56aef13fb05a6adc95eb9d8d66-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "T",
        "V",
        "N"
      ],
      "inputs": [
        "Text",
        "Video",
        "Latent / random seed"
      ],
      "description": "Diff. · NR · Video",
      "fields": {
        "Input": "Text, Video, Latent / random seed",
        "Mechanism": "Diff.",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C2",
      "name": "Make-A-Video",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Singer2023MakeAVideo",
      "title": "Make-A-Video: Text-to-Video Generation without Text-Video Data",
      "year": 2023,
      "venue": "International Conference on Learning Representations",
      "authors": "Singer, Uriel and Polyak, Adam and Hayes, Thomas and Yin, Xi and An, Jie and Zhang, Songyang and Hu, Qiyuan and Yang, Harry and Ashual, Oron and Gafni, Oran and Parikh, Devi and Gupta, Sonal and Taigman, Yaniv",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2209.14792",
      "doi": "",
      "arxiv": "2209.14792",
      "source": "manuscript/tables/catalogue-temporal.tex:26",
      "project_url": "",
      "url": "https://arxiv.org/abs/2209.14792",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "Diff. · NR · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "Diff.",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C3",
      "name": "Video LDM",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Blattmann2023VideoLDM",
      "title": "Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models",
      "year": 2023,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Blattmann, Andreas and Rombach, Robin and Ling, Huan and Dockhorn, Tim and Kim, Seung Wook and Fidler, Sanja and Kreis, Karsten",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2304.08818",
      "doi": "10.1109/cvpr52729.2023.02161",
      "arxiv": "2304.08818",
      "source": "manuscript/tables/catalogue-temporal.tex:28",
      "project_url": "",
      "url": "https://arxiv.org/abs/2304.08818",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "Diff. · Video latents · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "Diff.",
        "Representation / state": "Video latents",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C4",
      "name": "Imagen Video",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Ho2022ImagenVideo",
      "title": "Imagen Video: High Definition Video Generation with Diffusion Models",
      "year": 2022,
      "venue": "arXiv preprint arXiv:2210.02303",
      "authors": "Ho, Jonathan and Chan, William and Saharia, Chitwan and Whang, Jay and Gao, Ruiqi and Gritsenko, Alexey and Kingma, Diederik P. and Poole, Ben and Norouzi, Mohammad and Fleet, David J. and Salimans, Tim",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2210.02303",
      "doi": "",
      "arxiv": "2210.02303",
      "source": "manuscript/tables/catalogue-temporal.tex:29",
      "project_url": "",
      "url": "https://arxiv.org/abs/2210.02303",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "Diff. · NR · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "Diff.",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C5",
      "name": "Lumiere",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "BarTal2024Lumiere",
      "title": "Lumiere: A Space-Time Diffusion Model for Video Generation",
      "year": 2024,
      "venue": "SIGGRAPH Asia 2024 Conference Papers",
      "authors": "Bar-Tal, Omer and Chefer, Hila and Tov, Omer and Herrmann, Charles and Paiss, Roni and Zada, Shiran and Ephrat, Ariel and Hur, Junhwa and Liu, Guanghui and Raj, Amit and Li, Yuanzhen and Rubinstein, Michael and Michaeli, Tomer and Wang, Oliver and Sun, Deqing and Dekel, Tali and Mosseri, Inbar",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1145/3680528.3687614",
      "doi": "10.1145/3680528.3687614",
      "arxiv": "2401.12945",
      "source": "manuscript/tables/catalogue-temporal.tex:31",
      "project_url": "",
      "url": "https://doi.org/10.1145/3680528.3687614",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "V"
      ],
      "inputs": [
        "Text",
        "Image",
        "Video"
      ],
      "description": "Diff. · NR · Video",
      "fields": {
        "Input": "Text, Image, Video",
        "Mechanism": "Diff.",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C6",
      "name": "Stable Video Diff.",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Blattmann2023SVD",
      "title": "Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets",
      "year": 2023,
      "venue": "arXiv preprint arXiv:2311.15127",
      "authors": "Blattmann, Andreas and Dockhorn, Tim and Kulal, Sumith and Mendelevitch, Daniel and Kilian, Maciej and Lorenz, Dominik and Levi, Yam and English, Zion and Voleti, Vikram and Letts, Adam and Jampani, Varun and Rombach, Robin",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2311.15127",
      "doi": "",
      "arxiv": "2311.15127",
      "source": "manuscript/tables/catalogue-temporal.tex:32",
      "project_url": "",
      "url": "https://arxiv.org/abs/2311.15127",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "Diff. · Video latents · Video",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "Diff.",
        "Representation / state": "Video latents",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C7",
      "name": "VideoCrafter2",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Chen2024VideoCrafter2",
      "title": "VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models",
      "year": 2024,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Chen, Haoxin and Zhang, Yong and Cun, Xiaodong and Xia, Menghan and Wang, Xintao and Weng, Chao and Shan, Ying",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Chen_VideoCrafter2_Overcoming_Data_Limitations_for_High-Quality_Video_Diffusion_Models_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.00698",
      "arxiv": "2401.09047",
      "source": "manuscript/tables/catalogue-temporal.tex:34",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Chen_VideoCrafter2_Overcoming_Data_Limitations_for_High-Quality_Video_Diffusion_Models_CVPR_2024_paper.html",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "Diff. · NR · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "Diff.",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C8",
      "name": "HunyuanVideo",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Kong2024HunyuanVideo",
      "title": "HunyuanVideo: A Systematic Framework For Large Video Generative Models",
      "year": 2024,
      "venue": "arXiv preprint arXiv:2412.03603",
      "authors": "Kong, Weijie and Tian, Qi and Zhang, Zijian and Min, Rox and Dai, Zuozhuo and Zhou, Jin and Xiong, Jiangfeng and Li, Xin and Wu, Bo and Zhang, Jianwei and Wu, Kathrina and Lin, Qin and Yuan, Junkun and Long, Yanxin and Wang, Aladdin and Wang, Andong and Li, Changlin and Huang, Duojun and Yang, Fang and Tan, Hao and Wang, Hongmei and Song, Jacob and Bai, Jiawang and Wu, Jianbing and Xue, Jinbao and Wang, Joey and Wang, Kai and Liu, Mengyang and Li, Pengyu and Li, Shuai and Wang, Weiyan and Yu, Wenqing and Deng, Xinchi and Li, Yang and Chen, Yi and Cui, Yutao and Peng, Yuanbo and Yu, Zhentao and He, Zhiyu and Xu, Zhiyong and Zhou, Zixiang and Xu, Zunnan and Tao, Yangyu and Lu, Qinglin and Liu, Songtao and Zhou, Dax and Wang, Hongfa and Yang, Yong and Wang, Di and Liu, Yuhong and Jiang, Jie and Zhong, Caesar",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2412.03603",
      "doi": "",
      "arxiv": "2412.03603",
      "source": "manuscript/tables/catalogue-temporal.tex:35",
      "project_url": "",
      "url": "https://arxiv.org/abs/2412.03603",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "FM · Video latents · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "FM",
        "Representation / state": "Video latents",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C9",
      "name": "Wan",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Wan2025Wan",
      "title": "Wan: Open and Advanced Large-Scale Video Generative Models",
      "year": 2025,
      "venue": "arXiv preprint arXiv:2503.20314",
      "authors": "Wan Team and Wang, Ang and Ai, Baole and Wen, Bin and Mao, Chaojie and Xie, Chen-Wei and Chen, Di and Yu, Feiwu and Zhao, Haiming and Yang, Jianxiao and Zeng, Jianyuan and Wang, Jiayu and Zhang, Jingfeng and Zhou, Jingren and Wang, Jinkai and Chen, Jixuan and Zhu, Kai and Zhao, Kang and Yan, Keyu and Huang, Lianghua and Feng, Mengyang and Zhang, Ningyi and Li, Pandeng and Wu, Pingyu and Chu, Ruihang and Feng, Ruili and Zhang, Shiwei and Sun, Siyang and Fang, Tao and Wang, Tianxing and Gui, Tianyi and Weng, Tingyu and Shen, Tong and Lin, Wei and Wang, Wei and Wang, Wei and Zhou, Wenmeng and Wang, Wente and Shen, Wenting and Yu, Wenyuan and Shi, Xianzhong and Huang, Xiaoming and Xu, Xin and Kou, Yan and Lv, Yangyu and Li, Yifei and Liu, Yijing and Wang, Yiming and Zhang, Yingya and Huang, Yitong and Li, Yong and Wu, You and Liu, Yu and Pan, Yulin and Zheng, Yun and Hong, Yuntao and Shi, Yupeng and Feng, Yutong and Jiang, Zeyinzi and Han, Zhen and Wu, Zhi-Fan and Liu, Ziyu",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2503.20314",
      "doi": "",
      "arxiv": "2503.20314",
      "source": "manuscript/tables/catalogue-temporal.tex:37",
      "project_url": "",
      "url": "https://arxiv.org/abs/2503.20314",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "V"
      ],
      "inputs": [
        "Text",
        "Image",
        "Video"
      ],
      "description": "FM · Video latents · Video",
      "fields": {
        "Input": "Text, Image, Video",
        "Mechanism": "FM",
        "Representation / state": "Video latents",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C10",
      "name": "CogVideoX",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Yang2025CogVideoX",
      "title": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
      "year": 2025,
      "venue": "ICLR 2025",
      "authors": "Zhuoyi Yang and Jiayan Teng and Wendi Zheng and Ming Ding and Shiyu Huang and Jiazheng Xu and Yuanming Yang and Wenyi Hong and Xiaohan Zhang and Guanyu Feng and Da Yin and Yuxuan Zhang and Weihan Wang and Yean Cheng and Bin Xu and Xiaotao Gu and Yuxiao Dong and Jie Tang",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/ce31378e9f41d8907e97dab172b6c559-Paper-Conference.pdf",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:38",
      "project_url": "",
      "url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/ce31378e9f41d8907e97dab172b6c559-Paper-Conference.pdf",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "Diff. · Video latents · Video",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "Diff.",
        "Representation / state": "Video latents",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C11",
      "name": "Movie Gen",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Polyak2024MovieGen",
      "title": "Movie Gen: A Cast of Media Foundation Models",
      "year": 2024,
      "venue": "arXiv preprint arXiv:2410.13720",
      "authors": "Polyak, Adam and Zohar, Amit and Brown, Andrew and Tjandra, Andros and Sinha, Animesh and Lee, Ann and Vyas, Apoorv and Shi, Bowen and Ma, Chih-Yao and Chuang, Ching-Yao and Yan, David and Choudhary, Dhruv and Wang, Dingkang and Sethi, Geet and Pang, Guan and Ma, Haoyu and Misra, Ishan and Hou, Ji and Wang, Jialiang and Jagadeesh, Kiran and Li, Kunpeng and Zhang, Luxin and Singh, Mannat and Williamson, Mary and Le, Matt and Yu, Matthew and Singh, Mitesh Kumar and Zhang, Peizhao and Vajda, Peter and Duval, Quentin and Girdhar, Rohit and Sumbaly, Roshan and Rambhatla, Sai Saketh and Tsai, Sam and Azadi, Samaneh and Datta, Samyak and Chen, Sanyuan and Bell, Sean and Ramaswamy, Sharadh and Sheynin, Shelly and Bhattacharya, Siddharth and Motwani, Simran and Xu, Tao and Li, Tianhe and Hou, Tingbo and Hsu, Wei-Ning and Yin, Xi and Dai, Xiaoliang and Taigman, Yaniv and Luo, Yaqiao and Liu, Yen-Cheng and Wu, Yi-Chiao and Zhao, Yue and Kirstain, Yuval and He, Zecheng and He, Zijian and Pumarola, Albert and Thabet, Ali and Sanakoyeu, Artsiom and Mallya, Arun and Guo, Baishan and Araya, Boris and Kerr, Breena and Wood, Carleigh and Liu, Ce and Peng, Cen and Vengertsev, Dimitry and Schonfeld, Edgar and Blanchard, Elliot and Juefei-Xu, Felix and Nord, Fraylie and Liang, Jeff and Hoffman, John and Kohler, Jonas and Fire, Kaolin and Sivakumar, Karthik and Chen, Lawrence and Yu, Licheng and Gao, Luya and Georgopoulos, Markos and Moritz, Rashel and Sampson, Sara K. and Li, Shikai and Parmeggiani, Simone and Fine, Steve and Fowler, Tara and Petrovic, Vladan and Du, Yuming",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2410.13720",
      "doi": "",
      "arxiv": "2410.13720",
      "source": "manuscript/tables/catalogue-temporal.tex:40",
      "project_url": "",
      "url": "https://arxiv.org/abs/2410.13720",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "V"
      ],
      "inputs": [
        "Text",
        "Image",
        "Video"
      ],
      "description": "FM · Video latents · Video",
      "fields": {
        "Input": "Text, Image, Video",
        "Mechanism": "FM",
        "Representation / state": "Video latents",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C12",
      "name": "VideoGPT",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Yan2021VideoGPT",
      "title": "VideoGPT: Video Generation using VQ-VAE and Transformers",
      "year": 2021,
      "venue": "arXiv preprint arXiv:2104.10157",
      "authors": "Yan, Wilson and Zhang, Yunzhi and Abbeel, Pieter and Srinivas, Aravind",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2104.10157",
      "doi": "",
      "arxiv": "2104.10157",
      "source": "manuscript/tables/catalogue-temporal.tex:41",
      "project_url": "",
      "url": "https://arxiv.org/abs/2104.10157",
      "kind": "method",
      "input_tags": [
        "I",
        "A",
        "U"
      ],
      "inputs": [
        "Image",
        "Actions",
        "Unconditional"
      ],
      "description": "AR · Video tokens · Video",
      "fields": {
        "Input": "Image, Actions, Unconditional",
        "Mechanism": "AR",
        "Representation / state": "Video tokens",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C13",
      "name": "CogVideo",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Hong2023CogVideo",
      "title": "CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers",
      "year": 2023,
      "venue": "International Conference on Learning Representations",
      "authors": "Hong, Wenyi and Ding, Ming and Zheng, Wendi and Liu, Xinghan and Tang, Jie",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2205.15868",
      "doi": "",
      "arxiv": "2205.15868",
      "source": "manuscript/tables/catalogue-temporal.tex:43",
      "project_url": "",
      "url": "https://arxiv.org/abs/2205.15868",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "AR · NR · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "AR",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C14",
      "name": "Phenaki",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Villegas2023Phenaki",
      "title": "Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions",
      "year": 2023,
      "venue": "International Conference on Learning Representations",
      "authors": "Villegas, Ruben and Babaeizadeh, Mohammad and Kindermans, Pieter-Jan and Moraldo, Hernan and Zhang, Han and Saffar, Mohammad Taghi and Castro, Santiago and Kunze, Julius and Erhan, Dumitru",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2210.02399",
      "doi": "",
      "arxiv": "2210.02399",
      "source": "manuscript/tables/catalogue-temporal.tex:44",
      "project_url": "",
      "url": "https://arxiv.org/abs/2210.02399",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "MTM · Video tokens · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "MTM",
        "Representation / state": "Video tokens",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C15",
      "name": "MAGVIT",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Yu2023MAGVIT",
      "title": "MAGVIT: Masked Generative Video Transformer",
      "year": 2023,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Yu, Lijun and Cheng, Yong and Sohn, Kihyuk and Lezama, José and Zhang, Han and Chang, Huiwen and Hauptmann, Alexander G. and Yang, Ming-Hsuan and Hao, Yuan and Essa, Irfan and Jiang, Lu",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2212.05199",
      "doi": "10.1109/cvpr52729.2023.01008",
      "arxiv": "2212.05199",
      "source": "manuscript/tables/catalogue-temporal.tex:46",
      "project_url": "",
      "url": "https://arxiv.org/abs/2212.05199",
      "kind": "method",
      "input_tags": [
        "I",
        "V",
        "U"
      ],
      "inputs": [
        "Image",
        "Video",
        "Unconditional"
      ],
      "description": "MTM · Video tokens · Video",
      "fields": {
        "Input": "Image, Video, Unconditional",
        "Mechanism": "MTM",
        "Representation / state": "Video tokens",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C16",
      "name": "VideoPoet",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Kondratyuk2024VideoPoet",
      "title": "VideoPoet: A Large Language Model for Zero-Shot Video Generation",
      "year": 2024,
      "venue": "International Conference on Machine Learning",
      "authors": "Kondratyuk, Dan and Yu, Lijun and Gu, Xiuye and Lezama, José and Huang, Jonathan and Schindler, Grant and Hornung, Rachel and Birodkar, Vighnesh and Yan, Jimmy and Chiu, Ming-Chang and Somandepalli, Krishna and Akbari, Hassan and Alon, Yair and Cheng, Yong and Dillon, Josh and Gupta, Agrim and Hahn, Meera and Hauth, Anja and Hendon, David and Martinez, Alonso and Minnen, David and Sirotenko, Mikhail and Sohn, Kihyuk and Yang, Xuan and Adam, Hartwig and Yang, Ming-Hsuan and Essa, Irfan and Wang, Huisheng and Ross, David A. and Seybold, Bryan and Jiang, Lu",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2312.14125",
      "doi": "",
      "arxiv": "2312.14125",
      "source": "manuscript/tables/catalogue-temporal.tex:47",
      "project_url": "",
      "url": "https://arxiv.org/abs/2312.14125",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "V"
      ],
      "inputs": [
        "Text",
        "Image",
        "Video"
      ],
      "description": "AR · Multimodal tokens · Video",
      "fields": {
        "Input": "Text, Image, Video",
        "Mechanism": "AR",
        "Representation / state": "Multimodal tokens",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C17",
      "name": "NOVA",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Deng2025NOVA",
      "title": "Autoregressive Video Generation without Vector Quantization",
      "year": 2025,
      "venue": "International Conference on Learning Representations",
      "authors": "Deng, Haoge and Pan, Ting and Diao, Haiwen and Luo, Zhengxiong and Cui, Yufeng and Lu, Huchuan and Shan, Shiguang and Qi, Yonggang and Wang, Xinlong",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2412.14169",
      "doi": "",
      "arxiv": "2412.14169",
      "source": "manuscript/tables/catalogue-temporal.tex:49",
      "project_url": "",
      "url": "https://arxiv.org/abs/2412.14169",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "AR · Visual tokens · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "AR",
        "Representation / state": "Visual tokens",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C18",
      "name": "Lumos-1",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Yuan2026Lumos1",
      "title": "Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective",
      "year": 2026,
      "venue": "International Conference on Learning Representations",
      "authors": "Yuan, Hangjie and Chen, Weihua and Cen, Jun and Yu, Hu and Liang, Jingyun and Chang, Shuning and Lin, Zhihui and Feng, Tao and Liu, Pengwei and Xing, Jiazheng and Luo, Hao and Tang, Jiasheng and Wang, Fan and Yang, Yi",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2507.08801",
      "doi": "",
      "arxiv": "2507.08801",
      "source": "manuscript/tables/catalogue-temporal.tex:50",
      "project_url": "",
      "url": "https://arxiv.org/abs/2507.08801",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "AR+dDiff. · Video tokens · Video",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "AR+dDiff.",
        "Representation / state": "Video tokens",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C19",
      "name": "MAGI-1",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Teng2025MAGI1",
      "title": "MAGI-1: Autoregressive Video Generation at Scale",
      "year": 2025,
      "venue": "arXiv preprint arXiv:2505.13211",
      "authors": "Sand.ai and Teng, Hansi and Jia, Hongyu and Sun, Lei and Li, Lingzhi and Li, Maolin and Tang, Mingqiu and Han, Shuai and Zhang, Tianning and Zhang, W. Q. and Luo, Weifeng and Kang, Xiaoyang and Sun, Yuchen and Cao, Yue and Huang, Yunpeng and Lin, Yutong and Fang, Yuxin and Tao, Zewei and Zhang, Zheng and Wang, Zhongshu and Liu, Zixun and Shi, Dai and Su, Guoli and Sun, Hanwen and Pan, Hong and Wang, Jie and Sheng, Jiexin and Cui, Min and Hu, Min and Yan, Ming and Yin, Shucheng and Zhang, Siran and Liu, Tingting and Yin, Xianping and Yang, Xiaoyu and Song, Xin and Hu, Xuan and Zhang, Yankai and Li, Yuqiao",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2505.13211",
      "doi": "",
      "arxiv": "2505.13211",
      "source": "manuscript/tables/catalogue-temporal.tex:52",
      "project_url": "",
      "url": "https://arxiv.org/abs/2505.13211",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "AR+Diff. · NR · Video",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "AR+Diff.",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C20",
      "name": "EasyAnimate (V5 InP)",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Xu2024EasyAnimate",
      "title": "EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture",
      "year": 2024,
      "venue": "arXiv",
      "authors": "Jiaqi Xu and Xinyi Zou and Kunzhe Huang and Yunkuo Chen and Bo Liu and MengLi Cheng and Xing Shi and Jun Huang",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2405.18991v1",
      "doi": "10.48550/arXiv.2405.18991",
      "arxiv": "2405.18991",
      "source": "manuscript/tables/catalogue-temporal.tex:53",
      "project_url": "",
      "url": "https://arxiv.org/abs/2405.18991v1",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "Diff. · NR · Video",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "Diff.",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C21",
      "name": "Allegro (TI2V)",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Video generation and temporal priors",
      "bibkey": "Zhou2024Allegro",
      "title": "Allegro: Open the Black Box of Commercial-Level Video Generation Model",
      "year": 2024,
      "venue": "arXiv",
      "authors": "Yuan Zhou and Qiuyue Wang and Yuxuan Cai and Huan Yang",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2410.15458",
      "doi": "10.48550/arXiv.2410.15458",
      "arxiv": "2410.15458",
      "source": "manuscript/tables/catalogue-temporal.tex:55",
      "project_url": "",
      "url": "https://arxiv.org/abs/2410.15458",
      "kind": "method",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "NR · NR · Video",
      "fields": {
        "Input": "Text, Image",
        "Mechanism": "NR",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C22",
      "name": "4D-fy",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Time-varying 3D content",
      "bibkey": "Bahmani2024FourDfy",
      "title": "4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling",
      "year": 2024,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
      "authors": "Sherwin Bahmani and Ivan Skorokhodov and Victor Rong and Gordon Wetzstein and Leonidas Guibas and Peter Wonka and Sergey Tulyakov and Jeong Joon Park and Andrea Tagliasacchi and David B. Lindell",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1109/cvpr52733.2024.00764",
      "doi": "10.1109/cvpr52733.2024.00764",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:57",
      "project_url": "https://sherwinbahmani.github.io/4dfy/",
      "url": "https://sherwinbahmani.github.io/4dfy/",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "SD · Dynamic field · 4D scene",
      "fields": {
        "Input": "Text",
        "Mechanism": "SD",
        "Representation / state": "Dynamic field",
        "Output": "4D scene",
        "Stage": "P"
      }
    },
    {
      "id": "C23",
      "name": "DreamGaussian4D",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Time-varying 3D content",
      "bibkey": "Ren2023DreamGaussian4D",
      "title": "DreamGaussian4D: Generative 4D Gaussian Splatting",
      "year": 2023,
      "venue": "arXiv",
      "authors": "Jiawei Ren and Liang Pan and Jiaxiang Tang and Chi Zhang and Ang Cao and Gang Zeng and Ziwei Liu",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2312.17142v3",
      "doi": "10.48550/arXiv.2312.17142",
      "arxiv": "2312.17142",
      "source": "manuscript/tables/catalogue-temporal.tex:59",
      "project_url": "https://jiawei-ren.github.io/projects/dreamgaussian4d/",
      "url": "https://jiawei-ren.github.io/projects/dreamgaussian4d/",
      "kind": "method",
      "input_tags": [
        "I",
        "V"
      ],
      "inputs": [
        "Image",
        "Video"
      ],
      "description": "OPT · Deformable GS · Animated 3D asset",
      "fields": {
        "Input": "Image, Video",
        "Mechanism": "OPT",
        "Representation / state": "Deformable GS",
        "Output": "Animated 3D asset",
        "Stage": "P"
      }
    },
    {
      "id": "C24",
      "name": "MAV3D",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Time-varying 3D content",
      "bibkey": "Singer2023MAV3D",
      "title": "Text-To-4D Dynamic Scene Generation",
      "year": 2023,
      "venue": "ICML",
      "authors": "Uriel Singer and Shelly Sheynin and Adam Polyak and Oron Ashual and Iurii Makarov and Filippos Kokkinos and Naman Goyal and Andrea Vedaldi and Devi Parikh and Justin Johnson and Yaniv Taigman",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.mlr.press/v202/singer23a.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:60",
      "project_url": "",
      "url": "https://proceedings.mlr.press/v202/singer23a.html",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "SD · Dynamic field · 4D scene",
      "fields": {
        "Input": "Text",
        "Mechanism": "SD",
        "Representation / state": "Dynamic field",
        "Output": "4D scene",
        "Stage": "P"
      }
    },
    {
      "id": "C25",
      "name": "Consistent4D",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Time-varying 3D content",
      "bibkey": "Jiang2024Consistent4D",
      "title": "Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video",
      "year": 2024,
      "venue": "ICLR",
      "authors": "Jiang, Yanqin and Zhang, Li and Gao, Jin and Hu, Weiming and Yao, Yao",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.iclr.cc/paper_files/paper/2024/hash/e33a77969c26e5efdf3989ac46e7a036-Abstract-Conference.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:62",
      "project_url": "",
      "url": "https://proceedings.iclr.cc/paper_files/paper/2024/hash/e33a77969c26e5efdf3989ac46e7a036-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "V"
      ],
      "inputs": [
        "Video"
      ],
      "description": "Diff.+REC · Dynamic field · 4D object",
      "fields": {
        "Input": "Video",
        "Mechanism": "Diff.+REC",
        "Representation / state": "Dynamic field",
        "Output": "4D object",
        "Stage": "P"
      }
    },
    {
      "id": "C26",
      "name": "Align Your Gaussians",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Time-varying 3D content",
      "bibkey": "Ling2024AlignGaussians",
      "title": "Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models",
      "year": 2024,
      "venue": "CVPR",
      "authors": "Ling, Huan and Kim, Seung Wook and Torralba, Antonio and Fidler, Sanja and Kreis, Karsten",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2312.13763",
      "doi": "10.1109/cvpr52733.2024.00819",
      "arxiv": "2312.13763",
      "source": "manuscript/tables/catalogue-temporal.tex:63",
      "project_url": "",
      "url": "https://arxiv.org/abs/2312.13763",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "SD · Deformable GS · 4D animation",
      "fields": {
        "Input": "Text",
        "Mechanism": "SD",
        "Representation / state": "Deformable GS",
        "Output": "4D animation",
        "Stage": "P"
      }
    },
    {
      "id": "C27",
      "name": "Stable Video 4D",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Time-varying 3D content",
      "bibkey": "Xie2025SV4D",
      "title": "SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency",
      "year": 2025,
      "venue": "ICLR",
      "authors": "Xie, Yiming and Yao, Chun-Han and Voleti, Vikram and Jiang, Huaizu and Jampani, Varun",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/5297e56ac65ba2bfa70ee9fc4818c042-Abstract-Conference.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:65",
      "project_url": "",
      "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/5297e56ac65ba2bfa70ee9fc4818c042-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "V"
      ],
      "inputs": [
        "Video"
      ],
      "description": "Diff.+REC · Dynamic field · 4D object",
      "fields": {
        "Input": "Video",
        "Mechanism": "Diff.+REC",
        "Representation / state": "Dynamic field",
        "Output": "4D object",
        "Stage": "P"
      }
    },
    {
      "id": "C28",
      "name": "DimensionX",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Time-varying 3D content",
      "bibkey": "Sun2025DimensionX",
      "title": "DimensionX: Create Any 3D and 4D Scenes from a Single Image with Decoupled Video Diffusion",
      "year": 2025,
      "venue": "Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)",
      "authors": "Wenqiang Sun and Shuo Chen and Fangfu Liu and Zilong Chen and Yueqi Duan and Jun Zhu and Jun Zhang and Yikai Wang",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/ICCV2025/html/Sun_DimensionX_Create_Any_3D_and_4D_Scenes_from_a_Single_ICCV_2025_paper.html",
      "doi": "10.1109/iccv51701.2025.01271",
      "arxiv": "2411.04928",
      "source": "manuscript/tables/catalogue-temporal.tex:66",
      "project_url": "https://chenshuo20.github.io/DimensionX/",
      "url": "https://chenshuo20.github.io/DimensionX/",
      "kind": "method",
      "input_tags": [
        "I",
        "P"
      ],
      "inputs": [
        "Image",
        "Camera / pose"
      ],
      "description": "Diff.+REC · Space-time GS · 3D/4D scene",
      "fields": {
        "Input": "Image, Camera / pose",
        "Mechanism": "Diff.+REC",
        "Representation / state": "Space-time GS",
        "Output": "3D/4D scene",
        "Stage": "P"
      }
    },
    {
      "id": "C29",
      "name": "CAT4D",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Time-varying 3D content",
      "bibkey": "Wu2025CAT4D",
      "title": "CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models",
      "year": 2025,
      "venue": "CVPR",
      "authors": "Wu, Rundi and Gao, Ruiqi and Poole, Ben and Trevithick, Alex and Zheng, Changxi and Barron, Jonathan T. and Holynski, Aleksander",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2025/html/Wu_CAT4D_Create_Anything_in_4D_with_Multi-View_Video_Diffusion_Models_CVPR_2025_paper.html",
      "doi": "10.1109/cvpr52734.2025.02427",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:68",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2025/html/Wu_CAT4D_Create_Anything_in_4D_with_Multi-View_Video_Diffusion_Models_CVPR_2025_paper.html",
      "kind": "method",
      "input_tags": [
        "V",
        "P"
      ],
      "inputs": [
        "Video",
        "Camera / pose"
      ],
      "description": "Diff.+REC · Deformable GS · 4D scene",
      "fields": {
        "Input": "Video, Camera / pose",
        "Mechanism": "Diff.+REC",
        "Representation / state": "Deformable GS",
        "Output": "4D scene",
        "Stage": "P"
      }
    },
    {
      "id": "C30",
      "name": "Full-4D",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Time-varying 3D content",
      "bibkey": "Chen2026Full4D",
      "title": "Full-4D: Generating Full-Scope 4D Scenes from a Single-View Video",
      "year": 2026,
      "venue": "arXiv preprint arXiv:2605.25500",
      "authors": "Chen, Tingxi and Hao, Ke and Chen, Yabo and Cheng, Zhengxue and Xie, Rong and Song, Li and Huang, Haibin and Zhang, Chi and Li, Xuelong",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2605.25500v1",
      "doi": "10.48550/arXiv.2605.25500",
      "arxiv": "2605.25500",
      "source": "manuscript/tables/catalogue-temporal.tex:69",
      "project_url": "",
      "url": "https://arxiv.org/abs/2605.25500v1",
      "kind": "method",
      "input_tags": [
        "V",
        "P"
      ],
      "inputs": [
        "Video",
        "Camera / pose"
      ],
      "description": "Diff.+REC · Multiview video /deforming GS · Dynamic GS /views",
      "fields": {
        "Input": "Video, Camera / pose",
        "Mechanism": "Diff.+REC",
        "Representation / state": "Multiview video /deforming GS",
        "Output": "Dynamic GS /views",
        "Stage": "P"
      }
    },
    {
      "id": "C31",
      "name": "MotionCtrl",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Controlled and reference-guided video",
      "bibkey": "Wang2024MotionCtrl",
      "title": "MotionCtrl: A Unified and Flexible Motion Controller for Video Generation",
      "year": 2024,
      "venue": "SIGGRAPH Conference Papers",
      "authors": "Wang, Zhouxia and Yuan, Ziyang and Wang, Xintao and Li, Yaowei and Chen, Tianshui and Xia, Menghan and Luo, Ping and Shan, Ying",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2312.03641",
      "doi": "10.1145/3641519.3657518",
      "arxiv": "2312.03641",
      "source": "manuscript/tables/catalogue-temporal.tex:72",
      "project_url": "",
      "url": "https://arxiv.org/abs/2312.03641",
      "kind": "method",
      "input_tags": [
        "P",
        "M"
      ],
      "inputs": [
        "Camera / pose",
        "Motion / flow"
      ],
      "description": "CTRL · NR · Video",
      "fields": {
        "Input": "Camera / pose, Motion / flow",
        "Mechanism": "CTRL",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C32",
      "name": "CameraCtrl",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Controlled and reference-guided video",
      "bibkey": "He2025CameraCtrl",
      "title": "CameraCtrl: Enabling Camera Control for Video Diffusion Models",
      "year": 2025,
      "venue": "ICLR",
      "authors": "He, Hao and Xu, Yinghao and Guo, Yuwei and Wetzstein, Gordon and DAI, Bo and Li, Hongsheng and Yang, Ceyuan",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/f98fd73d59d8494489ea970747b91fe4-Abstract-Conference.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:73",
      "project_url": "",
      "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/f98fd73d59d8494489ea970747b91fe4-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "T",
        "P"
      ],
      "inputs": [
        "Text",
        "Camera / pose"
      ],
      "description": "Diff. · NR · Video",
      "fields": {
        "Input": "Text, Camera / pose",
        "Mechanism": "Diff.",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C33",
      "name": "Tune-A-Video",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Controlled and reference-guided video",
      "bibkey": "Wu2023TuneAVideo",
      "title": "Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation",
      "year": 2023,
      "venue": "Proceedings of the IEEE/CVF International Conference on Computer Vision",
      "authors": "Wu, Jay Zhangjie and Ge, Yixiao and Wang, Xintao and Lei, Stan Weixian and Gu, Yuchao and Shi, Yufei and Hsu, Wynne and Shan, Ying and Qie, Xiaohu and Shou, Mike Zheng",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/ICCV2023/html/Wu_Tune-A-Video_One-Shot_Tuning_of_Image_Diffusion_Models_for_Text-to-Video_Generation_ICCV_2023_paper.html",
      "doi": "10.1109/iccv51070.2023.00701",
      "arxiv": "2212.11565",
      "source": "manuscript/tables/catalogue-temporal.tex:75",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/ICCV2023/html/Wu_Tune-A-Video_One-Shot_Tuning_of_Image_Diffusion_Models_for_Text-to-Video_Generation_ICCV_2023_paper.html",
      "kind": "method",
      "input_tags": [
        "T",
        "V"
      ],
      "inputs": [
        "Text",
        "Video"
      ],
      "description": "Diff. · NR · Video",
      "fields": {
        "Input": "Text, Video",
        "Mechanism": "Diff.",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C34",
      "name": "AnimateDiff",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Controlled and reference-guided video",
      "bibkey": "Guo2024AnimateDiff",
      "title": "AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning",
      "year": 2024,
      "venue": "International Conference on Learning Representations",
      "authors": "Guo, Yuwei and Yang, Ceyuan and Rao, Anyi and Liang, Zhengyang and Wang, Yaohui and Qiao, Yu and Agrawala, Maneesh and Lin, Dahua and Dai, Bo",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2307.04725",
      "doi": "",
      "arxiv": "2307.04725",
      "source": "manuscript/tables/catalogue-temporal.tex:76",
      "project_url": "",
      "url": "https://arxiv.org/abs/2307.04725",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "Diff. · NR · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "Diff.",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C35",
      "name": "DynamiCrafter",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Controlled and reference-guided video",
      "bibkey": "Xing2024DynamiCrafter",
      "title": "DynamiCrafter: Animating Open-Domain Images with Video Diffusion Priors",
      "year": 2024,
      "venue": "Computer Vision - ECCV 2024",
      "authors": "Jinbo Xing and Menghan Xia and Yong Zhang and Haoxin Chen and Wangbo Yu and Hanyuan Liu and Gongye Liu and Xintao Wang and Ying Shan and Tien-Tsin Wong",
      "publication_type": "venue_publication",
      "paper_url": "https://link.springer.com/chapter/10.1007/978-3-031-72952-2_23",
      "doi": "10.1007/978-3-031-72952-2_23",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:78",
      "project_url": "",
      "url": "https://link.springer.com/chapter/10.1007/978-3-031-72952-2_23",
      "kind": "method",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "Diff. · Image-context features · Video",
      "fields": {
        "Input": "Image",
        "Mechanism": "Diff.",
        "Representation / state": "Image-context features",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C36",
      "name": "VideoComposer",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Controlled and reference-guided video",
      "bibkey": "Wang2023VideoComposer",
      "title": "VideoComposer: Compositional Video Synthesis with Motion Controllability",
      "year": 2023,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Wang, Xiang and Yuan, Hangjie and Zhang, Shiwei and Chen, Dayou and Wang, Jiuniu and Zhang, Yingya and Shen, Yujun and Zhao, Deli and Zhou, Jingren",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/180f6184a3458fa19c28c5483bc61877-Abstract-Conference.html",
      "doi": "10.52202/075280-0334",
      "arxiv": "2306.02018",
      "source": "manuscript/tables/catalogue-temporal.tex:79",
      "project_url": "",
      "url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/180f6184a3458fa19c28c5483bc61877-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "T",
        "V",
        "S",
        "M"
      ],
      "inputs": [
        "Text",
        "Video",
        "Sketch",
        "Motion / flow"
      ],
      "description": "Diff. · Space-time features · Video",
      "fields": {
        "Input": "Text, Video, Sketch, Motion / flow",
        "Mechanism": "Diff.",
        "Representation / state": "Space-time features",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C37",
      "name": "Matrix-Game 2.0",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Action-conditioned worlds and predictive models",
      "bibkey": "He2025MatrixGame2",
      "title": "Matrix-game 2.0: An open-source real-time and streaming interactive world model",
      "year": 2025,
      "venue": "arXiv",
      "authors": "Xianglong He and Chunli Peng and Zexiang Liu and Boyang Wang and Yifan Zhang and Qi Cui and Fei Kang and Biao Jiang and Mengyin An and Yangyang Ren and Baixin Xu and Hao-Xiang Guo and Kaixiong Gong and Cyrus Wu and Wei Li and Xuchen Song and Yang Liu and Eric Li and Yahui Zhou",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2508.13009v2",
      "doi": "10.48550/arXiv.2508.13009",
      "arxiv": "2508.13009",
      "source": "manuscript/tables/catalogue-temporal.tex:82",
      "project_url": "https://matrix-game-v2.github.io/",
      "url": "https://matrix-game-v2.github.io/",
      "kind": "method",
      "input_tags": [
        "I",
        "A"
      ],
      "inputs": [
        "Image",
        "Actions"
      ],
      "description": "AR+Diff. · Recent KV cache · Video",
      "fields": {
        "Input": "Image, Actions",
        "Mechanism": "AR+Diff.",
        "Representation / state": "Recent KV cache",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C38",
      "name": "Genie 3",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Action-conditioned worlds and predictive models",
      "bibkey": "ParkerHolder2025Genie3",
      "title": "Genie 3: A new frontier for world models",
      "year": 2025,
      "venue": "Official blog",
      "authors": "Jack Parker-Holder and Shlomi Fruchter",
      "publication_type": "official_blog",
      "paper_url": "https://deepmind.google/blog/genie-3-a-new-frontier-for-world-models/",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:83",
      "project_url": "https://deepmind.google/models/genie/",
      "url": "https://deepmind.google/models/genie/",
      "kind": "method",
      "input_tags": [
        "T",
        "A"
      ],
      "inputs": [
        "Text",
        "Actions"
      ],
      "description": "NR · NR · Video",
      "fields": {
        "Input": "Text, Actions",
        "Mechanism": "NR",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C39",
      "name": "Genie",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Action-conditioned worlds and predictive models",
      "bibkey": "Bruce2024Genie",
      "title": "Genie: Generative Interactive Environments",
      "year": 2024,
      "venue": "ICML",
      "authors": "Jake Bruce and Michael D Dennis and Ashley Edwards and Jack Parker-Holder and Yuge Shi and Edward Hughes and Matthew Lai and Aditi Mavalankar and Richie Steigerwald and Chris Apps and Yusuf Aytar and Sarah Maria Elisabeth Bechtle and Feryal Behbahani and Stephanie C.Y. Chan and Nicolas Heess and Lucy Gonzalez and Simon Osindero and Sherjil Ozair and Scott Reed and Jingwei Zhang and Konrad Zolna and Jeff Clune and Nando De Freitas and Satinder Singh and Tim Rocktäschel",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.mlr.press/v235/bruce24a.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:85",
      "project_url": "",
      "url": "https://proceedings.mlr.press/v235/bruce24a.html",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "S",
        "A"
      ],
      "inputs": [
        "Text",
        "Image",
        "Sketch",
        "Actions"
      ],
      "description": "AR · Video/action tokens · Video",
      "fields": {
        "Input": "Text, Image, Sketch, Actions",
        "Mechanism": "AR",
        "Representation / state": "Video/action tokens",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C40",
      "name": "GameNGen",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Action-conditioned worlds and predictive models",
      "bibkey": "Valevski2025GameNGen",
      "title": "Diffusion Models Are Real-Time Game Engines",
      "year": 2025,
      "venue": "ICLR",
      "authors": "Valevski, Dani and Leviathan, Yaniv and Arar, Moab and Fruchter, Shlomi",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/b71ecea210f7159f31e46631fe5c838f-Abstract-Conference.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:86",
      "project_url": "",
      "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/b71ecea210f7159f31e46631fe5c838f-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "V",
        "A"
      ],
      "inputs": [
        "Video",
        "Actions"
      ],
      "description": "AR+Diff. · Recent frame history · Video",
      "fields": {
        "Input": "Video, Actions",
        "Mechanism": "AR+Diff.",
        "Representation / state": "Recent frame history",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C41",
      "name": "DIAMOND",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Action-conditioned worlds and predictive models",
      "bibkey": "Alonso2024DIAMOND",
      "title": "Diffusion for World Modeling: Visual Details Matter in Atari",
      "year": 2024,
      "venue": "NeurIPS",
      "authors": "Eloi Alonso and Adam Jelley and Vincent Micheli and Anssi Kanervisto and Amos Storkey and Tim Pearce and Francois Fleuret",
      "publication_type": "venue_publication",
      "paper_url": "https://papers.neurips.cc/paper_files/paper/2024/file/6bdde0373d53d4a501249547084bed43-Paper-Conference.pdf",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:88",
      "project_url": "https://diamond-wm.github.io/",
      "url": "https://diamond-wm.github.io/",
      "kind": "method",
      "input_tags": [
        "V",
        "A"
      ],
      "inputs": [
        "Video",
        "Actions"
      ],
      "description": "AR+Diff. · Recent frame history · Predicted video",
      "fields": {
        "Input": "Video, Actions",
        "Mechanism": "AR+Diff.",
        "Representation / state": "Recent frame history",
        "Output": "Predicted video",
        "Stage": "R"
      }
    },
    {
      "id": "C42",
      "name": "Hunyuan-GameCraft",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Action-conditioned worlds and predictive models",
      "bibkey": "Li2025GameCraft",
      "title": "Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition",
      "year": 2025,
      "venue": "arXiv",
      "authors": "Li, Jiaqi and Tang, Junshu and Xu, Zhiyong and Wu, Longhuang and Zhou, Yuan and Shao, Shuai and Yu, Tianbao and Cao, Zhiguo and Lu, Qinglin",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2506.17201",
      "doi": "",
      "arxiv": "2506.17201",
      "source": "manuscript/tables/catalogue-temporal.tex:89",
      "project_url": "",
      "url": "https://arxiv.org/abs/2506.17201",
      "kind": "method",
      "input_tags": [
        "A",
        "P"
      ],
      "inputs": [
        "Actions",
        "Camera / pose"
      ],
      "description": "AR+Diff. · Historical context · Video",
      "fields": {
        "Input": "Actions, Camera / pose",
        "Mechanism": "AR+Diff.",
        "Representation / state": "Historical context",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C43",
      "name": "Hunyuan-GameCraft-2",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Action-conditioned worlds and predictive models",
      "bibkey": "Tang2025GameCraft2",
      "title": "Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model",
      "year": 2025,
      "venue": "arXiv",
      "authors": "Tang, Junshu and Liu, Jiacheng and Li, Jiaqi and Wu, Longhuang and Yang, Haoyu and Zhao, Penghao and Gong, Siruis and Yuan, Xiang and Shao, Shuai and Zhang, Linfeng and Lu, Qinglin",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2511.23429",
      "doi": "",
      "arxiv": "2511.23429",
      "source": "manuscript/tables/catalogue-temporal.tex:91",
      "project_url": "",
      "url": "https://arxiv.org/abs/2511.23429",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "A"
      ],
      "inputs": [
        "Text",
        "Image",
        "Actions"
      ],
      "description": "GEN · NR · Video",
      "fields": {
        "Input": "Text, Image, Actions",
        "Mechanism": "GEN",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C44",
      "name": "GameFactory",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Action-conditioned worlds and predictive models",
      "bibkey": "Yu2025GameFactory",
      "title": "GameFactory: Creating New Games with Generative Interactive Videos",
      "year": 2025,
      "venue": "Proceedings of the IEEE/CVF International Conference on Computer Vision",
      "authors": "Yu, Jiwen and Qin, Yiran and Wang, Xintao and Wan, Pengfei and Zhang, Di and Liu, Xihui",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2501.08325",
      "doi": "10.1109/iccv51701.2025.01078",
      "arxiv": "2501.08325",
      "source": "manuscript/tables/catalogue-temporal.tex:92",
      "project_url": "",
      "url": "https://arxiv.org/abs/2501.08325",
      "kind": "method",
      "input_tags": [
        "A"
      ],
      "inputs": [
        "Actions"
      ],
      "description": "AR+Diff. · NR · Video",
      "fields": {
        "Input": "Actions",
        "Mechanism": "AR+Diff.",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C45",
      "name": "Pandora",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Action-conditioned worlds and predictive models",
      "bibkey": "Xiang2024Pandora",
      "title": "Pandora: Towards General World Model with Natural Language Actions and Video States",
      "year": 2024,
      "venue": "arXiv preprint arXiv:2406.09455",
      "authors": "Xiang, Jiannan and Liu, Guangyi and Gu, Yi and Gao, Qiyue and Ning, Yuting and Zha, Yuheng and Feng, Zeyu and Tao, Tianhua and Hao, Shibo and Shi, Yemin and Liu, Zhengzhong and Xing, Eric P. and Hu, Zhiting",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2406.09455",
      "doi": "",
      "arxiv": "2406.09455",
      "source": "manuscript/tables/catalogue-temporal.tex:94",
      "project_url": "",
      "url": "https://arxiv.org/abs/2406.09455",
      "kind": "method",
      "input_tags": [
        "T",
        "A"
      ],
      "inputs": [
        "Text",
        "Actions"
      ],
      "description": "AR+Diff. · NR · Video",
      "fields": {
        "Input": "Text, Actions",
        "Mechanism": "AR+Diff.",
        "Representation / state": "NR",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C46",
      "name": "iVideoGPT",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Action-conditioned worlds and predictive models",
      "bibkey": "Wu2024iVideoGPT",
      "title": "iVideoGPT: Interactive VideoGPTs are Scalable World Models",
      "year": 2024,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Wu, Jialong and Yin, Shaofeng and Feng, Ningya and He, Xu and Li, Dong and Hao, Jianye and Long, Mingsheng",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2405.15223",
      "doi": "",
      "arxiv": "2405.15223",
      "source": "manuscript/tables/catalogue-temporal.tex:95",
      "project_url": "",
      "url": "https://arxiv.org/abs/2405.15223",
      "kind": "method",
      "input_tags": [
        "V",
        "A"
      ],
      "inputs": [
        "Video",
        "Actions"
      ],
      "description": "AR · Obs./action/reward · Predicted video",
      "fields": {
        "Input": "Video, Actions",
        "Mechanism": "AR",
        "Representation / state": "Obs./action/reward",
        "Output": "Predicted video",
        "Stage": "R"
      }
    },
    {
      "id": "C47",
      "name": "Vid2World",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Action-conditioned worlds and predictive models",
      "bibkey": "Huang2026Vid2World",
      "title": "Vid2World: Crafting Video Diffusion Models to Interactive World Models",
      "year": 2026,
      "venue": "International Conference on Learning Representations",
      "authors": "Huang, Siqiao and Wu, Jialong and Zhou, Qixing and Miao, Shangchen and Long, Mingsheng",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2505.14357",
      "doi": "",
      "arxiv": "2505.14357",
      "source": "manuscript/tables/catalogue-temporal.tex:97",
      "project_url": "",
      "url": "https://arxiv.org/abs/2505.14357",
      "kind": "method",
      "input_tags": [
        "V",
        "A"
      ],
      "inputs": [
        "Video",
        "Actions"
      ],
      "description": "AR+Diff. · NR · Predicted video",
      "fields": {
        "Input": "Video, Actions",
        "Mechanism": "AR+Diff.",
        "Representation / state": "NR",
        "Output": "Predicted video",
        "Stage": "R"
      }
    },
    {
      "id": "C48",
      "name": "DreamerV3",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Action-conditioned worlds and predictive models",
      "bibkey": "Hafner2025DreamerV3",
      "title": "Mastering diverse control tasks through world models",
      "year": 2025,
      "venue": "Nature",
      "authors": "Hafner, Danijar and Pasukonis, Jurgis and Ba, Jimmy and Lillicrap, Timothy",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1038/s41586-025-08744-2",
      "doi": "10.1038/s41586-025-08744-2",
      "arxiv": "2301.04104",
      "source": "manuscript/tables/catalogue-temporal.tex:98",
      "project_url": "",
      "url": "https://doi.org/10.1038/s41586-025-08744-2",
      "kind": "method",
      "input_tags": [
        "I",
        "A"
      ],
      "inputs": [
        "Image",
        "Actions"
      ],
      "description": "RSSM · Recurrent/stochastic state · Latent/reward predictions",
      "fields": {
        "Input": "Image, Actions",
        "Mechanism": "RSSM",
        "Representation / state": "Recurrent/stochastic state",
        "Output": "Latent/reward predictions",
        "Stage": "R"
      }
    },
    {
      "id": "C49",
      "name": "Solaris",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Action-conditioned worlds and predictive models",
      "bibkey": "Savva2026Solaris",
      "title": "Solaris: Building a Multiplayer Video World Model in Minecraft",
      "year": 2026,
      "venue": "arXiv preprint arXiv:2602.22208",
      "authors": "Savva, Georgy and Michel, Oscar and Lu, Daohan and Waiwitlikhit, Suppakit and Meehan, Timothy and Mishra, Dhairya and Poddar, Srivats and Lu, Jack and Xie, Saining",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2602.22208v2",
      "doi": "10.48550/arXiv.2602.22208",
      "arxiv": "2602.22208",
      "source": "manuscript/tables/catalogue-temporal.tex:100",
      "project_url": "https://solaris-wm.github.io/",
      "url": "https://solaris-wm.github.io/",
      "kind": "method",
      "input_tags": [
        "V",
        "A"
      ],
      "inputs": [
        "Video",
        "Actions"
      ],
      "description": "AR+Diff. · Per-player video latents /KV cache · Multiplayer videos",
      "fields": {
        "Input": "Video, Actions",
        "Mechanism": "AR+Diff.",
        "Representation / state": "Per-player video latents /KV cache",
        "Output": "Multiplayer videos",
        "Stage": "R"
      }
    },
    {
      "id": "C50",
      "name": "WorldPlay",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Sun2025WorldPlay",
      "title": "WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling",
      "year": 2026,
      "venue": "Proceedings of the 43rd International Conference on Machine Learning",
      "authors": "Wenqiang Sun and Haiyu Zhang and Haoyuan Wang and Junta Wu and Zehan Wang and Zhenwei Wang and Yunhong Wang and Jun Zhang and Tengfei Wang and Chunchao Guo",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.mlr.press/v306/sun26az.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:102",
      "project_url": "https://3d-models.hunyuan.tencent.com/world/?currentTab=HYWorld-1.5&lang=en",
      "url": "https://3d-models.hunyuan.tencent.com/world/?currentTab=HYWorld-1.5&lang=en",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "P",
        "A"
      ],
      "inputs": [
        "Text",
        "Image",
        "Camera / pose",
        "Actions"
      ],
      "description": "Diff. · Pose/frame memory · Video",
      "fields": {
        "Input": "Text, Image, Camera / pose, Actions",
        "Mechanism": "Diff.",
        "Representation / state": "Pose/frame memory",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C51",
      "name": "Matrix-Game 3.0",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Wang2026MatrixGame3",
      "title": "Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory",
      "year": 2026,
      "venue": "arXiv",
      "authors": "Zile Wang and Zexiang Liu and Jaixing Li and Kaichen Huang and Baixin Xu and Fei Kang and Mengyin An and Peiyu Wang and Biao Jiang and Yichen Wei and Yidan Xietian and Jiangbo Pei and Liang Hu and Boyi Jiang and Hua Xue and Zidong Wang and Haofeng Sun and Wei Li and Wanli Ouyang and Xianglong He and Yang Liu and Yangguang Li and Yahui Zhou",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2604.08995v1",
      "doi": "10.48550/arXiv.2604.08995",
      "arxiv": "2604.08995",
      "source": "manuscript/tables/catalogue-temporal.tex:104",
      "project_url": "https://matrix-game-v3.github.io/",
      "url": "https://matrix-game-v3.github.io/",
      "kind": "method",
      "input_tags": [
        "I",
        "P",
        "A"
      ],
      "inputs": [
        "Image",
        "Camera / pose",
        "Actions"
      ],
      "description": "AR+Diff. · Pose/frame memory · Video",
      "fields": {
        "Input": "Image, Camera / pose, Actions",
        "Mechanism": "AR+Diff.",
        "Representation / state": "Pose/frame memory",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C52",
      "name": "MultiGen",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Po2026MultiGen",
      "title": "MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines",
      "year": 2026,
      "venue": "arXiv",
      "authors": "Po, Ryan and Zhang, David Junhao and Hertz, Amir and Wetzstein, Gordon and Wadhwa, Neal and Ruiz, Nataniel",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2603.06679v2",
      "doi": "10.48550/arXiv.2603.06679",
      "arxiv": "2603.06679",
      "source": "manuscript/tables/catalogue-temporal.tex:105",
      "project_url": "https://ryanpo.com/multigen/",
      "url": "https://ryanpo.com/multigen/",
      "kind": "method",
      "input_tags": [
        "G",
        "P",
        "A"
      ],
      "inputs": [
        "Geometry",
        "Camera / pose",
        "Actions"
      ],
      "description": "Diff.+DYN · Map/player poses · Video +poses",
      "fields": {
        "Input": "Geometry, Camera / pose, Actions",
        "Mechanism": "Diff.+DYN",
        "Representation / state": "Map/player poses",
        "Output": "Video +poses",
        "Stage": "R"
      }
    },
    {
      "id": "C53",
      "name": "VMem",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Li2025VMem",
      "title": "VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory",
      "year": 2025,
      "venue": "ICCV",
      "authors": "Runjia Li and Philip Torr and Andrea Vedaldi and Tomas Jakab",
      "publication_type": "venue_publication",
      "paper_url": "https://v-mem.github.io/",
      "doi": "10.1109/iccv51701.2025.02383",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:107",
      "project_url": "https://v-mem.github.io/",
      "url": "https://v-mem.github.io/",
      "kind": "method",
      "input_tags": [
        "I",
        "P"
      ],
      "inputs": [
        "Image",
        "Camera / pose"
      ],
      "description": "AR+Diff. · Surfel-indexed views · Video",
      "fields": {
        "Input": "Image, Camera / pose",
        "Mechanism": "AR+Diff.",
        "Representation / state": "Surfel-indexed views",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C54",
      "name": "Long-term Spatial Memory",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Wu2025SpatialMemory",
      "title": "Video World Models with Long-term Spatial Memory",
      "year": 2025,
      "venue": "NeurIPS",
      "authors": "Wu, Tong and Yang, Shuai and Po, Ryan and Xu, Yinghao and Liu, Ziwei and Lin, Dahua and Wetzstein, Gordon",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2506.05284",
      "doi": "",
      "arxiv": "2506.05284",
      "source": "manuscript/tables/catalogue-temporal.tex:108",
      "project_url": "",
      "url": "https://arxiv.org/abs/2506.05284",
      "kind": "method",
      "input_tags": [
        "T",
        "V",
        "P"
      ],
      "inputs": [
        "Text",
        "Video",
        "Camera / pose"
      ],
      "description": "AR+Diff. · Point-map/frame memory · Video",
      "fields": {
        "Input": "Text, Video, Camera / pose",
        "Mechanism": "AR+Diff.",
        "Representation / state": "Point-map/frame memory",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C55",
      "name": "State-Space Video WM",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Po2025SSMWorld",
      "title": "Long-Context State-Space Video World Models",
      "year": 2025,
      "venue": "ICCV",
      "authors": "Po, Ryan and Nitzan, Yotam and Zhang, Richard and Chen, Berlin and Dao, Tri and Shechtman, Eli and Wetzstein, Gordon and Huang, Xun",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2505.20171",
      "doi": "10.1109/iccv51701.2025.00817",
      "arxiv": "2505.20171",
      "source": "manuscript/tables/catalogue-temporal.tex:110",
      "project_url": "",
      "url": "https://arxiv.org/abs/2505.20171",
      "kind": "method",
      "input_tags": [
        "A"
      ],
      "inputs": [
        "Actions"
      ],
      "description": "SSM+Diff. · Recurrent state · Video",
      "fields": {
        "Input": "Actions",
        "Mechanism": "SSM+Diff.",
        "Representation / state": "Recurrent state",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C56",
      "name": "ReWorld",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Chen2026ReWorld",
      "title": "ReWorld: An Interactive World Model with Long-Horizon Memory",
      "year": 2026,
      "venue": "arXiv",
      "authors": "Chen, Zhifei and Wang, Luozhou and Shen, Guibao and Yan, Dongyu and Yang, Shuai and Xu, Tianshuo and Du, Yihua and Wang, Wei and Gui, Tianyi and Huang, Lianghua and Chen, Yingcong",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2608.23565",
      "doi": "",
      "arxiv": "2608.23565",
      "source": "manuscript/tables/catalogue-temporal.tex:111",
      "project_url": "",
      "url": "https://arxiv.org/abs/2608.23565",
      "kind": "method",
      "input_tags": [
        "A",
        "P"
      ],
      "inputs": [
        "Actions",
        "Camera / pose"
      ],
      "description": "Diff. · KV/landmark memory · Video",
      "fields": {
        "Input": "Actions, Camera / pose",
        "Mechanism": "Diff.",
        "Representation / state": "KV/landmark memory",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C57",
      "name": "WorldMem",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Xiao2025WorldMem",
      "title": "WorldMem: Long-term Consistent World Simulation with Memory",
      "year": 2025,
      "venue": "NeurIPS",
      "authors": "Xiao, Zeqi and Lan, Yushi and Zhou, Yifan and Ouyang, Wenqi and Yang, Shuai and Zeng, Yanhong and Pan, Xingang",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/html/2504.12369v2",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:113",
      "project_url": "",
      "url": "https://arxiv.org/html/2504.12369v2",
      "kind": "method",
      "input_tags": [
        "V",
        "P",
        "A"
      ],
      "inputs": [
        "Video",
        "Camera / pose",
        "Actions"
      ],
      "description": "Diff. · Frame/pose/time memory · Video",
      "fields": {
        "Input": "Video, Camera / pose, Actions",
        "Mechanism": "Diff.",
        "Representation / state": "Frame/pose/time memory",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C58",
      "name": "PERSIST",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Garcin2026PERSIST",
      "title": "Beyond Pixel Histories: World Models with Persistent 3D State",
      "year": 2026,
      "venue": "ICML",
      "authors": "Samuel Garcin and Thomas Walker and Steven Mcdonagh and Tim Pearce and Hakan Bilen and Tianyu He and Kaixin Wang and Jiang Bian",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.mlr.press/v306/garcin26a.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-temporal.tex:114",
      "project_url": "",
      "url": "https://proceedings.mlr.press/v306/garcin26a.html",
      "kind": "method",
      "input_tags": [
        "I",
        "A",
        "G"
      ],
      "inputs": [
        "Image",
        "Actions",
        "Geometry"
      ],
      "description": "DYN · Latent 3D scene · Video",
      "fields": {
        "Input": "Image, Actions, Geometry",
        "Mechanism": "DYN",
        "Representation / state": "Latent 3D scene",
        "Output": "Video",
        "Stage": "A/R"
      }
    },
    {
      "id": "C59",
      "name": "FloWM",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Lillemark2026FloWM",
      "title": "Flow Equivariant World Models: Structured Memory for Dynamic Environments",
      "year": 2026,
      "venue": "Proceedings of the 43rd International Conference on Machine Learning",
      "authors": "Lillemark, Hansen and Huang, Benhao and Zhan, Fangneng and Du, Yilun and Keller, T. Anderson",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.mlr.press/v306/lillemark26a.html",
      "doi": "",
      "arxiv": "2601.01075",
      "source": "manuscript/tables/catalogue-temporal.tex:116",
      "project_url": "https://flowequivariantworldmodels.github.io/",
      "url": "https://flowequivariantworldmodels.github.io/",
      "kind": "method",
      "input_tags": [
        "V",
        "A"
      ],
      "inputs": [
        "Video",
        "Actions"
      ],
      "description": "DYN · Latent spatial map /velocity channels · Predicted video",
      "fields": {
        "Input": "Video, Actions",
        "Mechanism": "DYN",
        "Representation / state": "Latent spatial map /velocity channels",
        "Output": "Predicted video",
        "Stage": "R"
      }
    },
    {
      "id": "C60",
      "name": "LiveWorld",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Duan2026LiveWorld",
      "title": "LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models",
      "year": 2026,
      "venue": "arXiv preprint arXiv:2603.07145",
      "authors": "Duan, Zicheng and Xia, Jiatong and Zhang, Zeyu and Zhang, Wenbo and Zhou, Gengze and Gou, Chenhui and He, Yefei and Chen, Feng and Zhang, Xinyu and Liu, Lingqiao",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2603.07145v2",
      "doi": "10.48550/arXiv.2603.07145",
      "arxiv": "2603.07145",
      "source": "manuscript/tables/catalogue-temporal.tex:117",
      "project_url": "https://zichengduan.github.io/pages/LiveWorld/",
      "url": "https://zichengduan.github.io/pages/LiveWorld/",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "P"
      ],
      "inputs": [
        "Text",
        "Image",
        "Camera / pose"
      ],
      "description": "Diff.+DYN · Static geometry /entity states · Camera-conditioned video",
      "fields": {
        "Input": "Text, Image, Camera / pose",
        "Mechanism": "Diff.+DYN",
        "Representation / state": "Static geometry /entity states",
        "Output": "Camera-conditioned video",
        "Stage": "R"
      }
    },
    {
      "id": "C61",
      "name": "AnchorWeave",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Wang2026AnchorWeave",
      "title": "AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories",
      "year": 2026,
      "venue": "Computer Vision – ECCV 2026",
      "authors": "Wang, Zun and Lin, Han and Yoon, Jaehong and Cho, Jaemin and Zhang, Yue and Bansal, Mohit",
      "publication_type": "venue_publication",
      "paper_url": "https://link.springer.com/chapter/10.1007/978-3-032-37356-4_12",
      "doi": "10.1007/978-3-032-37356-4_12",
      "arxiv": "2602.14941",
      "source": "manuscript/tables/catalogue-temporal.tex:119",
      "project_url": "https://zunwang1.github.io/AnchorWeave",
      "url": "https://zunwang1.github.io/AnchorWeave",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "V",
        "P"
      ],
      "inputs": [
        "Text",
        "Image",
        "Video",
        "Camera / pose"
      ],
      "description": "Diff. · Retrieved local point clouds /poses · Camera-controlled video",
      "fields": {
        "Input": "Text, Image, Video, Camera / pose",
        "Mechanism": "Diff.",
        "Representation / state": "Retrieved local point clouds /poses",
        "Output": "Camera-controlled video",
        "Stage": "R"
      }
    },
    {
      "id": "C62",
      "name": "ActWorld",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Xiong2026ActWorld",
      "title": "ActWorld: From Explorable to Interactive World Model via Action-Aware Memory",
      "year": 2026,
      "venue": "arXiv preprint arXiv:2606.17730",
      "authors": "Xiong, Zhexiao and Song, Yizhi and Kang, Hao and Yan, Qing and Jiang, Liming and Yang, Jenson and Fu, Zhoujie and Fotiadis, Stathi and Wang, Angtian and Liu, Zichuan and Liu, Bo and Yang, Yiding and Lu, Xin and Jacobs, Nathan",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2606.17730v1",
      "doi": "10.48550/arXiv.2606.17730",
      "arxiv": "2606.17730",
      "source": "manuscript/tables/catalogue-temporal.tex:120",
      "project_url": "",
      "url": "https://arxiv.org/abs/2606.17730v1",
      "kind": "method",
      "input_tags": [
        "T",
        "V",
        "P",
        "A"
      ],
      "inputs": [
        "Text",
        "Video",
        "Camera / pose",
        "Actions"
      ],
      "description": "AR+Diff. · Ranked history /event /identity tokens · Action-conditioned video",
      "fields": {
        "Input": "Text, Video, Camera / pose, Actions",
        "Mechanism": "AR+Diff.",
        "Representation / state": "Ranked history /event /identity tokens",
        "Output": "Action-conditioned video",
        "Stage": "R"
      }
    },
    {
      "id": "C63",
      "name": "Programmable World Model",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Huang2026ProgrammableWorld",
      "title": "Programmable World Model",
      "year": 2026,
      "venue": "arXiv preprint arXiv:2609.10540",
      "authors": "Huang, Zheng-Hui and Lin, Guixu and Lin, Jiacheng and Huang, Yi-Chuan and Yu, Ruihan and Niu, Muyao and Yang, Siqi and Liu, Yu-Lun and Chuang, Yung-Yu and Zhang, Kaipeng and Wang, Zhixiang",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2609.10540v2",
      "doi": "10.48550/arXiv.2609.10540",
      "arxiv": "2609.10540",
      "source": "manuscript/tables/catalogue-temporal.tex:122",
      "project_url": "https://alaya-lab.github.io/pwm/",
      "url": "https://alaya-lab.github.io/pwm/",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "P",
        "A"
      ],
      "inputs": [
        "Text",
        "Image",
        "Camera / pose",
        "Actions"
      ],
      "description": "Diff.+DYN · Entity IDs /3D boxes /rules · State-conditioned video",
      "fields": {
        "Input": "Text, Image, Camera / pose, Actions",
        "Mechanism": "Diff.+DYN",
        "Representation / state": "Entity IDs /3D boxes /rules",
        "Output": "State-conditioned video",
        "Stage": "A/R"
      }
    },
    {
      "id": "C64",
      "name": "WorldDirector",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Spatial memory and persistent state",
      "bibkey": "Wang2026WorldDirector",
      "title": "WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory",
      "year": 2026,
      "venue": "arXiv preprint arXiv:2607.02517",
      "authors": "Wang, Hanlin and Ouyang, Hao and Wang, Qiuyu and Wang, Wen and Bai, Qingyan and Cheng, Ka Leong and Yu, Yue and Li, Yixuan and Meng, Yihao and Liu, Zichen and Zeng, Yanhong and Shen, Yujun and Chen, Qifeng",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2607.02517v1",
      "doi": "10.48550/arXiv.2607.02517",
      "arxiv": "2607.02517",
      "source": "manuscript/tables/catalogue-temporal.tex:123",
      "project_url": "https://worlddirector.github.io/",
      "url": "https://worlddirector.github.io/",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "P"
      ],
      "inputs": [
        "Text",
        "Image",
        "Camera / pose"
      ],
      "description": "Diff.+CTRL · 3D boxes /appearance /memory · Controlled video",
      "fields": {
        "Input": "Text, Image, Camera / pose",
        "Mechanism": "Diff.+CTRL",
        "Representation / state": "3D boxes /appearance /memory",
        "Output": "Controlled video",
        "Stage": "R"
      }
    },
    {
      "id": "C65",
      "name": "Diffusion Forcing",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Long-form and streaming generation",
      "bibkey": "Chen2024DiffusionForcing",
      "title": "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion",
      "year": 2024,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Chen, Boyuan and Martí Monsó, Diego and Du, Yilun and Simchowitz, Max and Tedrake, Russ and Sitzmann, Vincent",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2407.01392",
      "doi": "",
      "arxiv": "2407.01392",
      "source": "manuscript/tables/catalogue-temporal.tex:126",
      "project_url": "",
      "url": "https://arxiv.org/abs/2407.01392",
      "kind": "method",
      "input_tags": [],
      "inputs": [],
      "description": "Diff. · Sequence tokens · Predicted sequences",
      "fields": {
        "Input": "NR",
        "Mechanism": "Diff.",
        "Representation / state": "Sequence tokens",
        "Output": "Predicted sequences",
        "Stage": "P/R"
      }
    },
    {
      "id": "C66",
      "name": "History-Guided VD",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Long-form and streaming generation",
      "bibkey": "Song2025HistoryGuidance",
      "title": "History-Guided Video Diffusion",
      "year": 2025,
      "venue": "International Conference on Machine Learning",
      "authors": "Song, Kiwhan and Chen, Boyuan and Simchowitz, Max and Du, Yilun and Tedrake, Russ and Sitzmann, Vincent",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2502.06764",
      "doi": "",
      "arxiv": "2502.06764",
      "source": "manuscript/tables/catalogue-temporal.tex:127",
      "project_url": "",
      "url": "https://arxiv.org/abs/2502.06764",
      "kind": "method",
      "input_tags": [
        "V"
      ],
      "inputs": [
        "Video"
      ],
      "description": "Diff. · Frame history · Video",
      "fields": {
        "Input": "Video",
        "Mechanism": "Diff.",
        "Representation / state": "Frame history",
        "Output": "Video",
        "Stage": "P/R"
      }
    },
    {
      "id": "C67",
      "name": "CausVid",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Long-form and streaming generation",
      "bibkey": "Yin2025CausVid",
      "title": "From Slow Bidirectional to Fast Autoregressive Video Diffusion Models",
      "year": 2025,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Yin, Tianwei and Zhang, Qiang and Zhang, Richard and Freeman, William T. and Durand, Fredo and Shechtman, Eli and Huang, Xun",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2412.07772",
      "doi": "10.1109/cvpr52734.2025.02138",
      "arxiv": "2412.07772",
      "source": "manuscript/tables/catalogue-temporal.tex:129",
      "project_url": "",
      "url": "https://arxiv.org/abs/2412.07772",
      "kind": "method",
      "input_tags": [
        "T",
        "I",
        "V"
      ],
      "inputs": [
        "Text",
        "Image",
        "Video"
      ],
      "description": "Diff.+DIST · KV cache · Video",
      "fields": {
        "Input": "Text, Image, Video",
        "Mechanism": "Diff.+DIST",
        "Representation / state": "KV cache",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C68",
      "name": "Self Forcing",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Long-form and streaming generation",
      "bibkey": "Huang2025SelfForcing",
      "title": "Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion",
      "year": 2025,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Huang, Xun and Li, Zhengqi and He, Guande and Zhou, Mingyuan and Shechtman, Eli",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2506.08009",
      "doi": "",
      "arxiv": "2506.08009",
      "source": "manuscript/tables/catalogue-temporal.tex:130",
      "project_url": "",
      "url": "https://arxiv.org/abs/2506.08009",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "AR+Diff. · Rolling KV cache · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "AR+Diff.",
        "Representation / state": "Rolling KV cache",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C69",
      "name": "FreeNoise",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Long-form and streaming generation",
      "bibkey": "Qiu2024FreeNoise",
      "title": "FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling",
      "year": 2024,
      "venue": "International Conference on Learning Representations",
      "authors": "Qiu, Haonan and Xia, Menghan and Zhang, Yong and He, Yingqing and Wang, Xintao and Shan, Ying and Liu, Ziwei",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2310.15169",
      "doi": "",
      "arxiv": "2310.15169",
      "source": "manuscript/tables/catalogue-temporal.tex:132",
      "project_url": "",
      "url": "https://arxiv.org/abs/2310.15169",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "Diff. · Correlated noise windows · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "Diff.",
        "Representation / state": "Correlated noise windows",
        "Output": "Video",
        "Stage": "P"
      }
    },
    {
      "id": "C70",
      "name": "FIFO-Diffusion",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Long-form and streaming generation",
      "bibkey": "Kim2024FIFODiffusion",
      "title": "FIFO-Diffusion: Generating Infinite Videos from Text without Training",
      "year": 2024,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Kim, Jihwan and Kang, Junoh and Choi, Jinyoung and Han, Bohyung",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2405.11473",
      "doi": "",
      "arxiv": "2405.11473",
      "source": "manuscript/tables/catalogue-temporal.tex:133",
      "project_url": "",
      "url": "https://arxiv.org/abs/2405.11473",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "Diff. · Latent frame queue · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "Diff.",
        "Representation / state": "Latent frame queue",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C71",
      "name": "StreamingT2V",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Long-form and streaming generation",
      "bibkey": "Henschel2025StreamingT2V",
      "title": "StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text",
      "year": 2025,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Henschel, Roberto and Khachatryan, Levon and Poghosyan, Hayk and Hayrapetyan, Daniil and Tadevosyan, Vahram and Wang, Zhangyang and Navasardyan, Shant and Shi, Humphrey",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2025/html/Henschel_StreamingT2V_Consistent_Dynamic_and_Extendable_Long_Video_Generation_from_Text_CVPR_2025_paper.html",
      "doi": "10.1109/cvpr52734.2025.00245",
      "arxiv": "2403.14773",
      "source": "manuscript/tables/catalogue-temporal.tex:135",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2025/html/Henschel_StreamingT2V_Consistent_Dynamic_and_Extendable_Long_Video_Generation_from_Text_CVPR_2025_paper.html",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "AR+Diff. · Context/appearance features · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "AR+Diff.",
        "Representation / state": "Context/appearance features",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "C72",
      "name": "LongLive",
      "category": "temporal",
      "category_label": "Temporal content & worlds",
      "group": "Long-form and streaming generation",
      "bibkey": "Yang2026LongLive",
      "title": "LongLive: Real-time Interactive Long Video Generation",
      "year": 2026,
      "venue": "International Conference on Learning Representations",
      "authors": "Yang, Shuai and Huang, Wei and Chu, Ruihang and Xiao, Yicheng and Zhao, Yuyang and Wang, Xianbang and Li, Muyang and Xie, Enze and Chen, Yingcong and Lu, Yao and Han, Song and Chen, Yukang",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.iclr.cc/paper_files/paper/2026/hash/91a1610c6ed9e02d33f826b46f472b92-Abstract-Conference.html",
      "doi": "",
      "arxiv": "2509.22622",
      "source": "manuscript/tables/catalogue-temporal.tex:136",
      "project_url": "",
      "url": "https://proceedings.iclr.cc/paper_files/paper/2026/hash/91a1610c6ed9e02d33f826b46f472b92-Abstract-Conference.html",
      "kind": "method",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "AR · Refreshed KV cache · Video",
      "fields": {
        "Input": "Text",
        "Mechanism": "AR",
        "Representation / state": "Refreshed KV cache",
        "Output": "Video",
        "Stage": "R"
      }
    },
    {
      "id": "X1",
      "name": "VRCopilot",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Spatial authoring and situated creation",
      "bibkey": "Zhang2024VRCopilot",
      "title": "VRCopilot: Authoring 3D Layouts with Generative AI Models in VR",
      "year": 2024,
      "venue": "Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology",
      "authors": "Lei Zhang and Jin Pan and Jacob Gettig and Steve Oney and Anhong Guo",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1145/3654777.3676451",
      "doi": "10.1145/3654777.3676451",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:29",
      "project_url": "https://from.so/papers/vrcopilot_authoring_3d_layouts_with_generative_models_in_vr_2024/",
      "url": "https://from.so/papers/vrcopilot_authoring_3d_layouts_with_generative_models_in_vr_2024/",
      "kind": "system",
      "input_tags": [
        "Sp",
        "S",
        "C"
      ],
      "inputs": [
        "Speech",
        "Sketch",
        "Controller / touch / manipulation"
      ],
      "description": "Layout+library objects · Quest 2 · Layout",
      "fields": {
        "Input": "Speech, Sketch, Controller / touch / manipulation",
        "Model / component": "ATISS",
        "Artifact": "Layout+library objects",
        "Platform": "Quest 2",
        "Task": "Layout",
        "Evaluation": "U"
      }
    },
    {
      "id": "X2",
      "name": "Dreamcrafter",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Spatial authoring and situated creation",
      "bibkey": "Vachha2025Dreamcrafter",
      "title": "Dreamcrafter: Immersive Editing of 3D Radiance Fields Through Flexible, Generative Inputs and Outputs",
      "year": 2025,
      "venue": "Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems",
      "authors": "Cyrus Vachha and Yixiao Kang and Zach Dive and Ashwat Chidambaram and Anik Gupta and Eunice Jun and Björn Hartmann",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1145/3706598.3714312",
      "doi": "10.1145/3706598.3714312",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:30",
      "project_url": "https://dream-crafter.github.io/",
      "url": "https://dream-crafter.github.io/",
      "kind": "system",
      "input_tags": [
        "Sp",
        "G",
        "C"
      ],
      "inputs": [
        "Speech",
        "Geometry / scene context",
        "Controller / touch / manipulation"
      ],
      "description": "Images/GS/meshes · Quest 3+PC · Preview",
      "fields": {
        "Input": "Speech, Geometry / scene context, Controller / touch / manipulation",
        "Model / component": "Modular gen.",
        "Artifact": "Images/GS/meshes",
        "Platform": "Quest 3+PC",
        "Task": "Preview",
        "Evaluation": "X"
      }
    },
    {
      "id": "X3",
      "name": "GaussianShopVR",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Spatial authoring and situated creation",
      "bibkey": "Shen2025GaussianShopVR",
      "title": "GaussianShopVR: Facilitating Immersive 3D Authoring Using Gaussian Splatting in VR",
      "year": 2025,
      "venue": "UIST 2025",
      "authors": "Yulin Shen and Boyu Li and Jiayang Huang and David Yip and Zeyu Wang",
      "publication_type": "venue_publication",
      "paper_url": "https://cislab.hkust-gz.edu.cn/projects/gaussianshopvr/",
      "doi": "10.1145/3746059.3747803",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:32",
      "project_url": "https://cislab.hkust-gz.edu.cn/projects/gaussianshopvr/",
      "url": "https://cislab.hkust-gz.edu.cn/projects/gaussianshopvr/",
      "kind": "system",
      "input_tags": [
        "G",
        "S"
      ],
      "inputs": [
        "Geometry / scene context",
        "Sketch"
      ],
      "description": "Edited/new GS · VR · 3D editing",
      "fields": {
        "Input": "Geometry / scene context, Sketch",
        "Model / component": "3DGS editing",
        "Artifact": "Edited/new GS",
        "Platform": "VR",
        "Task": "3D editing",
        "Evaluation": "U"
      }
    },
    {
      "id": "X4",
      "name": "DreamSpace",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Spatial authoring and situated creation",
      "bibkey": "Yang2024DreamSpace",
      "title": "DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagation",
      "year": 2024,
      "venue": "IEEE VR 2024",
      "authors": "Bangbang Yang and Wenqi Dong and Lin Ma and Wenbo Hu and Xiao Liu and Zhaopeng Cui and Yuewen Ma",
      "publication_type": "venue_publication",
      "paper_url": "https://ybbbbt.com/publication/dreamspace/",
      "doi": "10.1109/VR58804.2024.00085",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:33",
      "project_url": "https://ybbbbt.com/publication/dreamspace/",
      "url": "https://ybbbbt.com/publication/dreamspace/",
      "kind": "system",
      "input_tags": [
        "T",
        "G"
      ],
      "inputs": [
        "Text",
        "Geometry / scene context"
      ],
      "description": "Textured scene mesh · HMD VR · Stylization",
      "fields": {
        "Input": "Text, Geometry / scene context",
        "Model / component": "Panoramic diffusion",
        "Artifact": "Textured scene mesh",
        "Platform": "HMD VR",
        "Task": "Stylization",
        "Evaluation": "T/D"
      }
    },
    {
      "id": "X5",
      "name": "Generative terrain",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Spatial authoring and situated creation",
      "bibkey": "Hu2024GenerativeTerrain",
      "title": "Generative Terrain Authoring with Mid-air Hand Sketching in Virtual Reality",
      "year": 2024,
      "venue": "ACM VRST 2024",
      "authors": "Yushen Hu and Keru Wang and Yuli Shao and Jan Plass and Zhu Wang and Ken Perlin",
      "publication_type": "venue_publication",
      "paper_url": "https://cs.unm.edu/~zhuwang/assets/pdf/VR_Terrain_Generation_VRST_2024.pdf",
      "doi": "10.1145/3641825.3687736",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:35",
      "project_url": "",
      "url": "https://cs.unm.edu/~zhuwang/assets/pdf/VR_Terrain_Generation_VRST_2024.pdf",
      "kind": "system",
      "input_tags": [
        "H",
        "S"
      ],
      "inputs": [
        "Hand",
        "Sketch"
      ],
      "description": "Height-map terrain · Quest 3 · Terrain",
      "fields": {
        "Input": "Hand, Sketch",
        "Model / component": "CGAN",
        "Artifact": "Height-map terrain",
        "Platform": "Quest 3",
        "Task": "Terrain",
        "Evaluation": "U"
      }
    },
    {
      "id": "X6",
      "name": "Roomify",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Spatial authoring and situated creation",
      "bibkey": "Wang2026Roomify",
      "title": "Roomify: Spatially-Grounded Style Transformation for Immersive Virtual Environments",
      "year": 2026,
      "venue": "CHI 2026",
      "authors": "Xueyang Wang and Qinxuan Cen and Weitao Bi and Yunxiang Ma and Xin Yi and Robert Xiao and Xinyi Fu and Hewu Li",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2603.04917",
      "doi": "10.1145/3772318.3791803",
      "arxiv": "2603.04917",
      "source": "manuscript/tables/catalogue-xr.tex:36",
      "project_url": "",
      "url": "https://arxiv.org/abs/2603.04917",
      "kind": "system",
      "input_tags": [
        "V",
        "T",
        "I"
      ],
      "inputs": [
        "Video",
        "Text",
        "Image"
      ],
      "description": "Stylized environment · Quest 3 · Room edit",
      "fields": {
        "Input": "Video, Text, Image",
        "Model / component": "gpt-image-1/Tripo2.5",
        "Artifact": "Stylized environment",
        "Platform": "Quest 3",
        "Task": "Room edit",
        "Evaluation": "U"
      }
    },
    {
      "id": "X7",
      "name": "ImaginateAR",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Spatial authoring and situated creation",
      "bibkey": "Lee2025ImaginateAR",
      "title": "ImaginateAR: AI-Assisted In-Situ Authoring in Augmented Reality",
      "year": 2025,
      "venue": "Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology",
      "authors": "Lee, Jaewook and Aleotti, Filippo and Mazala, Diego and Garcia-Hernando, Guillermo and Vicente, Sara and Johnston, Oliver James and Kraus-Liang, Isabel and Powierza, Jakub and Shin, Donghoon and Froehlich, Jon E. and Brostow, Gabriel and Van Brummelen, Jessica",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1145/3746059.3747635",
      "doi": "10.1145/3746059.3747635",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:38",
      "project_url": "https://nianticspatial.github.io/imaginatear/",
      "url": "https://nianticspatial.github.io/imaginatear/",
      "kind": "system",
      "input_tags": [
        "T",
        "C",
        "G"
      ],
      "inputs": [
        "Text",
        "Controller / touch / manipulation",
        "Geometry / scene context"
      ],
      "description": "Placed meshes · Phone AR · Situated",
      "fields": {
        "Input": "Text, Controller / touch / manipulation, Geometry / scene context",
        "Model / component": "Graph-guided gen.",
        "Artifact": "Placed meshes",
        "Platform": "Phone AR",
        "Task": "Situated",
        "Evaluation": "T/U"
      }
    },
    {
      "id": "X8",
      "name": "Context-aware 3D",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Spatial authoring and situated creation",
      "bibkey": "Behravan2025ContextAware3D",
      "title": "Generative AI for Context-Aware 3D Object Creation Using Vision-Language Models in Augmented Reality",
      "year": 2025,
      "venue": "IEEE AIxVR 2025",
      "authors": "Majid Behravan and Krešimir Matković and Denis Gračanin",
      "publication_type": "venue_publication",
      "paper_url": "https://www.vrvis.at/en/publications/PB-VRVis-2025-022",
      "doi": "10.1109/AIxVR63409.2025.00018",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:39",
      "project_url": "",
      "url": "https://www.vrvis.at/en/publications/PB-VRVis-2025-022",
      "kind": "system",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "3D objects · AR headset · Context",
      "fields": {
        "Input": "Image",
        "Model / component": "LLaVA+3D generator",
        "Artifact": "3D objects",
        "Platform": "AR headset",
        "Task": "Context",
        "Evaluation": "T/R"
      }
    },
    {
      "id": "X9",
      "name": "Dream Mesh",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Spatial authoring and situated creation",
      "bibkey": "Weng2024DreamMesh",
      "title": "Dream Mesh: A Speech-to-3D Model Generative Pipeline in Mixed Reality",
      "year": 2024,
      "venue": "IEEE AIxVR 2024",
      "authors": "Suibi Che-Chuan Weng and Yan-Ming Chiou and Ellen Yi-Luen Do",
      "publication_type": "venue_publication",
      "paper_url": "https://www.researchgate.net/publication/378580267_Dream_Mesh_A_Speech-to-3D_Model_Generative_Pipeline_in_Mixed_Reality",
      "doi": "10.1109/AIxVR59861.2024.00059",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:41",
      "project_url": "",
      "url": "https://www.researchgate.net/publication/378580267_Dream_Mesh_A_Speech-to-3D_Model_Generative_Pipeline_in_Mixed_Reality",
      "kind": "system",
      "input_tags": [
        "Sp"
      ],
      "inputs": [
        "Speech"
      ],
      "description": "Imported mesh · Quest Pro · Objects",
      "fields": {
        "Input": "Speech",
        "Model / component": "DreamFusion/ThreeStudio",
        "Artifact": "Imported mesh",
        "Platform": "Quest Pro",
        "Task": "Objects",
        "Evaluation": "D"
      }
    },
    {
      "id": "X10",
      "name": "Editing Reality",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Spatial authoring and situated creation",
      "bibkey": "Weng2026EditingReality",
      "title": "Editing Reality: Designing In-Situ Co-Creation with Generative AI in Mixed Reality",
      "year": 2026,
      "venue": "DIS 2026",
      "authors": "Suibi Che-Chuan Weng and Shih-Yu Ma and Sawyer Reinig and Pritalee Kadam and Ada Yi Zhao and Amy Banić and Ryo Suzuki and Ellen Yi-Luen Do",
      "publication_type": "venue_publication",
      "paper_url": "https://www.colorado.edu/atlas/editing-reality-situ-co-creation-generative-ai-mixed-reality",
      "doi": "10.1145/3800645.3813087",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:42",
      "project_url": "https://www.colorado.edu/atlas/editing-reality-situ-co-creation-generative-ai-mixed-reality",
      "url": "https://www.colorado.edu/atlas/editing-reality-situ-co-creation-generative-ai-mixed-reality",
      "kind": "system",
      "input_tags": [
        "Sp",
        "S",
        "C",
        "G"
      ],
      "inputs": [
        "Speech",
        "Sketch",
        "Controller / touch / manipulation",
        "Geometry / scene context"
      ],
      "description": "Edited scene elements · MR · Co-creation",
      "fields": {
        "Input": "Speech, Sketch, Controller / touch / manipulation, Geometry / scene context",
        "Model / component": "Modular gen.",
        "Artifact": "Edited scene elements",
        "Platform": "MR",
        "Task": "Co-creation",
        "Evaluation": "F/E"
      }
    },
    {
      "id": "X11",
      "name": "ImmerseGen",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Spatial authoring and situated creation",
      "bibkey": "Yuan2026ImmerseGen",
      "title": "ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies",
      "year": 2026,
      "venue": "IEEE Transactions on Visualization and Computer Graphics",
      "authors": "Jinyan Yuan and Bangbang Yang and Keke Wang and Panwang Pan and Lin Ma and Xuehai Zhang and Xiao Liu and Zhaopeng Cui and Yuewen Ma",
      "publication_type": "venue_publication",
      "paper_url": "https://immersegen.github.io/",
      "doi": "10.1109/TVCG.2026.3679097",
      "arxiv": "2506.14315",
      "source": "manuscript/tables/catalogue-xr.tex:44",
      "project_url": "https://immersegen.github.io/",
      "url": "https://immersegen.github.io/",
      "kind": "system",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "Alpha-textured meshes · PICO 4 Ultra /XR2 Gen 2 · Immersive worlds",
      "fields": {
        "Input": "Text",
        "Model / component": "GPT-4o /SDXL-ControlNet /layered diff.",
        "Artifact": "Alpha-textured meshes",
        "Platform": "PICO 4 Ultra /XR2 Gen 2",
        "Task": "Immersive worlds",
        "Evaluation": "T/U"
      }
    },
    {
      "id": "X12",
      "name": "MS2Mesh-XR",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Object creation, prototyping, and collaboration",
      "bibkey": "Tong2025MS2MeshXR",
      "title": "MS2Mesh-XR: Multi-Modal Sketch-to-Mesh Generation in XR Environments",
      "year": 2025,
      "venue": "2025 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)",
      "authors": "Yuqi Tong and Yue Qiu and Ruiyang Li and Shi Qiu and Pheng-Ann Heng",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1109/AIxVR63409.2025.00052",
      "doi": "10.1109/AIxVR63409.2025.00052",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:46",
      "project_url": "https://yueqiu0911.github.io/MS2Mesh-XR/",
      "url": "https://yueqiu0911.github.io/MS2Mesh-XR/",
      "kind": "system",
      "input_tags": [
        "Sp",
        "S",
        "H"
      ],
      "inputs": [
        "Speech",
        "Sketch",
        "Hand"
      ],
      "description": "OBJ mesh · Quest 3 · Objects",
      "fields": {
        "Input": "Speech, Sketch, Hand",
        "Model / component": "ControlNet1.1/CRM",
        "Artifact": "OBJ mesh",
        "Platform": "Quest 3",
        "Task": "Objects",
        "Evaluation": "D/T"
      }
    },
    {
      "id": "X13",
      "name": "CoGen3D",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Object creation, prototyping, and collaboration",
      "bibkey": "Jiang2026CoGen3D",
      "title": "CoGen3D: An Agentic Human-AI Co-Design Pipeline for 3D Asset Generation for Virtual Reality",
      "year": 2026,
      "venue": "arXiv",
      "authors": "Weiwei Jiang and Wanyu He and Zheyu Tan and Zheyuan Kuang and Difeng Yu and Shinobu Hasegawa and Sven Mayer and Zhanna Sarsenbayeva",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2607.03731v1",
      "doi": "10.48550/arXiv.2607.03731",
      "arxiv": "2607.03731",
      "source": "manuscript/tables/catalogue-xr.tex:48",
      "project_url": "",
      "url": "https://arxiv.org/abs/2607.03731v1",
      "kind": "system",
      "input_tags": [
        "T"
      ],
      "inputs": [
        "Text"
      ],
      "description": "GLB mesh · Desktop→Quest 3 · Co-design",
      "fields": {
        "Input": "Text",
        "Model / component": "FLUX.1/Hunyuan3D-2",
        "Artifact": "GLB mesh",
        "Platform": "Desktop→Quest 3",
        "Task": "Co-design",
        "Evaluation": "U"
      }
    },
    {
      "id": "X14",
      "name": "Say It, See It",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Object creation, prototyping, and collaboration",
      "bibkey": "Xiu2025SayItSeeIt",
      "title": "Say It, See It: A Systematic Evaluation on Speech-Based 3D Content Generation Methods in Augmented Reality",
      "year": 2025,
      "venue": "IEEE ISMAR Adjunct 2025; UNAI workshop",
      "authors": "Yanming Xiu and Joshua Chilukuri and Shunav Sen and Maria Gorlatova",
      "publication_type": "venue_publication",
      "paper_url": "https://scholars.duke.edu/publication/1705223",
      "doi": "10.1109/ISMAR-Adjunct68609.2025.00069",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:49",
      "project_url": "",
      "url": "https://scholars.duke.edu/publication/1705223",
      "kind": "system",
      "input_tags": [
        "Sp"
      ],
      "inputs": [
        "Speech"
      ],
      "description": "3D objects · Quest 3 · Speech-to-3D",
      "fields": {
        "Input": "Speech",
        "Model / component": "Modular 3D pipelines",
        "Artifact": "3D objects",
        "Platform": "Quest 3",
        "Task": "Speech-to-3D",
        "Evaluation": "U/T"
      }
    },
    {
      "id": "X15",
      "name": "Gesture2Prop",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Object creation, prototyping, and collaboration",
      "bibkey": "Yao2025Gesture2Prop",
      "title": "Gesture2Prop: Conditional VR Prop Generation from Hand Gestures and Speech",
      "year": 2025,
      "venue": "UIST Adjunct 2025",
      "authors": "Zhihao Yao and Xiwen Yao and Qirui Sun and Haowei Xiong and Kin Wang Lau and Haipeng Mi",
      "publication_type": "venue_publication",
      "paper_url": "https://haowei-xiong-sowilo-research-station.webflow.io/post/posts/gesture2prop-conditional-vr-prop-generation-from-handgestures-and-speech",
      "doi": "10.1145/3746058.3759017",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:51",
      "project_url": "",
      "url": "https://haowei-xiong-sowilo-research-station.webflow.io/post/posts/gesture2prop-conditional-vr-prop-generation-from-handgestures-and-speech",
      "kind": "system",
      "input_tags": [
        "Sp",
        "H"
      ],
      "inputs": [
        "Speech",
        "Hand"
      ],
      "description": "3D props · Quest 3 · Props",
      "fields": {
        "Input": "Speech, Hand",
        "Model / component": "ControlNet+3D reconstruction",
        "Artifact": "3D props",
        "Platform": "Quest 3",
        "Task": "Props",
        "Evaluation": "D"
      }
    },
    {
      "id": "X16",
      "name": "FusionProtor",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Object creation, prototyping, and collaboration",
      "bibkey": "Zhang2025FusionProtor",
      "title": "FusionProtor: A Mixed-Prototype Tool for Component-level Physical-to-Virtual 3D Transition and Simulation",
      "year": 2025,
      "venue": "CHI 2025",
      "authors": "Hongbo Zhang and Pei Chen and Xuelong Xie and Zhaoqu Jiang and Yifei Wu and Zejian Li and Xiaoyu Chen and Lingyun Sun",
      "publication_type": "venue_publication",
      "paper_url": "https://hongboooo.github.io/files/fusion.pdf",
      "doi": "10.1145/3706598.3713686",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:52",
      "project_url": "",
      "url": "https://hongboooo.github.io/files/fusion.pdf",
      "kind": "system",
      "input_tags": [
        "I",
        "T",
        "C"
      ],
      "inputs": [
        "Image",
        "Text",
        "Controller / touch / manipulation"
      ],
      "description": "3D components · Apple Vision Pro · Prototyping",
      "fields": {
        "Input": "Image, Text, Controller / touch / manipulation",
        "Model / component": "SDXL-1.0/Rodin",
        "Artifact": "3D components",
        "Platform": "Apple Vision Pro",
        "Task": "Prototyping",
        "Evaluation": "T/U"
      }
    },
    {
      "id": "X17",
      "name": "Thing2Reality",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Object creation, prototyping, and collaboration",
      "bibkey": "Hu2025Thing2Reality",
      "title": "Thing2Reality: Enabling Spontaneous Creation of 3D Objects from 2D Content using Generative AI in XR Meetings",
      "year": 2025,
      "venue": "UIST 2025",
      "authors": "Erzhen Hu and Mingyi Li and Jungtaek Hong and Xun Qian and Alex Olwal and David Kim and Seongkook Heo and Ruofei Du",
      "publication_type": "venue_publication",
      "paper_url": "https://erzhenh.com/pdfs/uist25_Thing2Reality.pdf",
      "doi": "10.1145/3746059.3747621",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:54",
      "project_url": "",
      "url": "https://erzhenh.com/pdfs/uist25_Thing2Reality.pdf",
      "kind": "system",
      "input_tags": [
        "I",
        "V",
        "S"
      ],
      "inputs": [
        "Image",
        "Video",
        "Sketch"
      ],
      "description": "Views/3D Gaussians · Quest 3 · Discussion",
      "fields": {
        "Input": "Image, Video, Sketch",
        "Model / component": "Image-to-3D",
        "Artifact": "Views/3D Gaussians",
        "Platform": "Quest 3",
        "Task": "Discussion",
        "Evaluation": "U"
      }
    },
    {
      "id": "X18",
      "name": "SpaceBlender",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Object creation, prototyping, and collaboration",
      "bibkey": "Numan2024SpaceBlender",
      "title": "SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending",
      "year": 2024,
      "venue": "UIST 2024",
      "authors": "Nels Numan and Shwetha Rajaram and Balasaravanan Thoravi Kumaravel and Nicolai Marquardt and Andrew D. Wilson",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2409.13926",
      "doi": "10.1145/3654777.3676361",
      "arxiv": "2409.13926",
      "source": "manuscript/tables/catalogue-xr.tex:55",
      "project_url": "",
      "url": "https://arxiv.org/abs/2409.13926",
      "kind": "system",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "Shared scene mesh · Quest 3 · Blending",
      "fields": {
        "Input": "Image",
        "Model / component": "ControlNet-Layout",
        "Artifact": "Shared scene mesh",
        "Platform": "Quest 3",
        "Task": "Blending",
        "Evaluation": "U"
      }
    },
    {
      "id": "X19",
      "name": "CreepyCoCreator",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Object creation, prototyping, and collaboration",
      "bibkey": "Rasch2025CreepyCoCreator",
      "title": "CreepyCoCreator? Investigating AI Representation Modes for 3D Object Co-Creation in Virtual Reality",
      "year": 2025,
      "venue": "CHI 2025",
      "authors": "Julian Rasch and Julia Töws and Teresa Hirzle and Florian Müller and Martin Schmitz",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2502.03069",
      "doi": "10.1145/3706598.3713720",
      "arxiv": "2502.03069",
      "source": "manuscript/tables/catalogue-xr.tex:57",
      "project_url": "",
      "url": "https://arxiv.org/abs/2502.03069",
      "kind": "system",
      "input_tags": [
        "C"
      ],
      "inputs": [
        "Controller / touch / manipulation"
      ],
      "description": "Co-created object · Quest Pro · Co-creation",
      "fields": {
        "Input": "Controller / touch / manipulation",
        "Model / component": "Scripted alternatives",
        "Artifact": "Co-created object",
        "Platform": "Quest Pro",
        "Task": "Co-creation",
        "Evaluation": "WoZ"
      }
    },
    {
      "id": "X20",
      "name": "PartInteractor",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Object creation, prototyping, and collaboration",
      "bibkey": "Jiang2026PartInteractor",
      "title": "PartInteractor: Intent-Driven Part-Aware 3D Authoring for Continuous Co-Creation in XR",
      "year": 2026,
      "venue": "arXiv",
      "authors": "Jianan Jiang and Bin Li",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2608.01335v1",
      "doi": "10.48550/arXiv.2608.01335",
      "arxiv": "2608.01335",
      "source": "manuscript/tables/catalogue-xr.tex:58",
      "project_url": "https://horizonjohn.github.io/PartInteractor/",
      "url": "https://horizonjohn.github.io/PartInteractor/",
      "kind": "system",
      "input_tags": [
        "Sp",
        "S",
        "I",
        "H",
        "G"
      ],
      "inputs": [
        "Speech",
        "Sketch",
        "Image",
        "Hand",
        "Geometry / scene context"
      ],
      "description": "Part-structured GLB · Quest 3 +PC +APIs · Part editing",
      "fields": {
        "Input": "Speech, Sketch, Image, Hand, Geometry / scene context",
        "Model / component": "GPT-4o /GPT-Image-1 /OmniPart",
        "Artifact": "Part-structured GLB",
        "Platform": "Quest 3 +PC +APIs",
        "Task": "Part editing",
        "Evaluation": "U/T"
      }
    },
    {
      "id": "X21",
      "name": "VideoCraft",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Video and behavior authoring",
      "bibkey": "Li2025VideoCraft",
      "title": "VideoCraft: A Mixed Reality-empowered Video Generation Workflow with Spatial Layer Editing for Concept Video Creation",
      "year": 2025,
      "venue": "UIST 2025",
      "authors": "Boyu Li and Lin-Ping Yuan and Zeyu Wang",
      "publication_type": "venue_publication",
      "paper_url": "https://cislab.hkust-gz.edu.cn/publications/videocraft-a-mixed-reality-empowered-video-generation-workflow-with-spatial-layer-editing-for-concept-video-creation/",
      "doi": "10.1145/3746059.3747606",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:61",
      "project_url": "",
      "url": "https://cislab.hkust-gz.edu.cn/publications/videocraft-a-mixed-reality-empowered-video-generation-workflow-with-spatial-layer-editing-for-concept-video-creation/",
      "kind": "system",
      "input_tags": [
        "V",
        "G"
      ],
      "inputs": [
        "Video",
        "Geometry / scene context"
      ],
      "description": "Concept video · MR · Video edit",
      "fields": {
        "Input": "Video, Geometry / scene context",
        "Model / component": "Video-to-video",
        "Artifact": "Concept video",
        "Platform": "MR",
        "Task": "Video edit",
        "Evaluation": "U/E"
      }
    },
    {
      "id": "X22",
      "name": "LLMR",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Video and behavior authoring",
      "bibkey": "DeLaTorre2024LLMR",
      "title": "LLMR: Real-time Prompting of Interactive Worlds using Large Language Models",
      "year": 2024,
      "venue": "CHI 2024",
      "authors": "De La Torre, Fernanda and Cathy Mengying Fang and Han Huang and Andrzej Banburski-Fahey and Judith Amores Fernandez and Jaron Lanier",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2309.12276",
      "doi": "10.1145/3613904.3642579",
      "arxiv": "2309.12276",
      "source": "manuscript/tables/catalogue-xr.tex:62",
      "project_url": "https://llm4mr.github.io/",
      "url": "https://llm4mr.github.io/",
      "kind": "system",
      "input_tags": [
        "T",
        "G"
      ],
      "inputs": [
        "Text",
        "Geometry / scene context"
      ],
      "description": "Scene code · Desktop/AR/VR · Worlds",
      "fields": {
        "Input": "Text, Geometry / scene context",
        "Model / component": "GPT-4",
        "Artifact": "Scene code",
        "Platform": "Desktop/AR/VR",
        "Task": "Worlds",
        "Evaluation": "T/U"
      }
    },
    {
      "id": "X23",
      "name": "ImoGenXR",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Video and behavior authoring",
      "bibkey": "Limbert2025ImoGenXR",
      "title": "ImoGenXR: Investigating the Impact on Creativity Support in a Generative-AI Assisted Immersive Authoring Workflow",
      "year": 2025,
      "venue": "11th International Conference on Virtual Reality (ICVR 2025)",
      "authors": "George Limbert and Abhijit Karnik",
      "publication_type": "venue_publication",
      "paper_url": "https://eprints.lancs.ac.uk/229355/1/VR1013.pdf",
      "doi": "10.1109/ICVR66534.2025.11172549",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:64",
      "project_url": "",
      "url": "https://eprints.lancs.ac.uk/229355/1/VR1013.pdf",
      "kind": "system",
      "input_tags": [
        "Sp",
        "C"
      ],
      "inputs": [
        "Speech",
        "Controller / touch / manipulation"
      ],
      "description": "Models+behavior scripts · VR · Behavior",
      "fields": {
        "Input": "Speech, Controller / touch / manipulation",
        "Model / component": "GPT-4o+retrieval",
        "Artifact": "Models+behavior scripts",
        "Platform": "VR",
        "Task": "Behavior",
        "Evaluation": "U"
      }
    },
    {
      "id": "X24",
      "name": "HOICraft",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Video and behavior authoring",
      "bibkey": "Lee2026HOICraft",
      "title": "HOICraft: In-Situ VLM-based Authoring Tool for Part-Level Hand-Object Interaction Design in VR",
      "year": 2026,
      "venue": "Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems",
      "authors": "Lee, Dohui and Sun, Qi and Yoon, Sang Ho",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1145/3772318.3790823",
      "doi": "10.1145/3772318.3790823",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:65",
      "project_url": "",
      "url": "https://doi.org/10.1145/3772318.3790823",
      "kind": "system",
      "input_tags": [
        "G",
        "H"
      ],
      "inputs": [
        "Geometry / scene context",
        "Hand"
      ],
      "description": "HOI mappings · Quest 3+PC · HOI",
      "fields": {
        "Input": "Geometry / scene context, Hand",
        "Model / component": "GPT-4o",
        "Artifact": "HOI mappings",
        "Platform": "Quest 3+PC",
        "Task": "HOI",
        "Evaluation": "U"
      }
    },
    {
      "id": "X25",
      "name": "GenAssist",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Video and behavior authoring",
      "bibkey": "Srinidhi2026GenAssist",
      "title": "GenAssist: Interactive Prompt-Driven XR Program Generation",
      "year": 2026,
      "venue": "2026 IEEE Conference on Virtual Reality and 3D User Interfaces (VR)",
      "authors": "Sruti Srinidhi and Akul Singh and Edward Lu and Anthony Rowe",
      "publication_type": "venue_publication",
      "paper_url": "https://www.srutisrinidhi.com/GenAssist/",
      "doi": "10.1109/VR67842.2026.00081",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:67",
      "project_url": "https://www.srutisrinidhi.com/GenAssist/",
      "url": "https://www.srutisrinidhi.com/GenAssist/",
      "kind": "system",
      "input_tags": [
        "T",
        "G"
      ],
      "inputs": [
        "Text",
        "Geometry / scene context"
      ],
      "description": "Scene /interaction code · ARENA /browser /WebXR · XR programs",
      "fields": {
        "Input": "Text, Geometry / scene context",
        "Model / component": "GPT-4o +doc./model RAG",
        "Artifact": "Scene /interaction code",
        "Platform": "ARENA /browser /WebXR",
        "Task": "XR programs",
        "Evaluation": "T/U/R"
      }
    },
    {
      "id": "X26",
      "name": "Generated Reality",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Presentation and action response",
      "bibkey": "Xie2026GeneratedReality",
      "title": "Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control",
      "year": 2026,
      "venue": "CVPR 2026 Findings",
      "authors": "Xie, Linxi and Sun, Lisong C. and Neall, Ashley and Wu, Tong and Cai, Shengqu and Wetzstein, Gordon",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2602.18422v1",
      "doi": "10.1109/cvprf71909.2026.00387",
      "arxiv": "2602.18422",
      "source": "manuscript/tables/catalogue-xr.tex:69",
      "project_url": "https://codeysun.github.io/generated-reality/",
      "url": "https://codeysun.github.io/generated-reality/",
      "kind": "system",
      "input_tags": [
        "T",
        "P",
        "H"
      ],
      "inputs": [
        "Text",
        "Head / pose",
        "Hand"
      ],
      "description": "Video · Quest 3 · Action response",
      "fields": {
        "Input": "Text, Head / pose, Hand",
        "Model / component": "5B video diffusion",
        "Artifact": "Video",
        "Platform": "Quest 3",
        "Task": "Action response",
        "Evaluation": "U/T"
      }
    },
    {
      "id": "X27",
      "name": "EPIC",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Presentation and action response",
      "bibkey": "Mandal2026EPIC",
      "title": "EPIC: Epipolar-Consistent 360-Degree Immersive Stereo Video Generation",
      "year": 2026,
      "venue": "arXiv",
      "authors": "Mandal, Debabrata and Fu, Dongdong and Miller, Jonathon and Villareal, William and Peng, Xi and Chakravarthula, Praneeth",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2609.38689v1",
      "doi": "10.48550/arXiv.2609.38689",
      "arxiv": "2609.38689",
      "source": "manuscript/tables/catalogue-xr.tex:71",
      "project_url": "",
      "url": "https://arxiv.org/abs/2609.38689v1",
      "kind": "system",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "ODS stereo video · VR-target · Stereo",
      "fields": {
        "Input": "Text, Image",
        "Model / component": "Stereo video diffusion",
        "Artifact": "ODS stereo video",
        "Platform": "VR-target",
        "Task": "Stereo",
        "Evaluation": "T"
      }
    },
    {
      "id": "X28",
      "name": "Heritage prototyping",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Presentation and action response",
      "bibkey": "Liu2026HeritagePrototyping",
      "title": "Generative AI-Assisted Visualization Prototyping for Cultural Heritage: A Computational Framework from 2D Planes to 3D Immersive Scenes",
      "year": 2026,
      "venue": "Buildings",
      "authors": "Liu, Jianquan and Li, Runnan and Zhao, Haiying",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.3390/buildings16163319",
      "doi": "10.3390/buildings16163319",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:72",
      "project_url": "",
      "url": "https://doi.org/10.3390/buildings16163319",
      "kind": "system",
      "input_tags": [
        "I"
      ],
      "inputs": [
        "Image"
      ],
      "description": "Assets+scene fragments · PICO 4/video · Heritage",
      "fields": {
        "Input": "Image",
        "Model / component": "Hunyuan hosted models",
        "Artifact": "Assets+scene fragments",
        "Platform": "PICO 4/video",
        "Task": "Heritage",
        "Evaluation": "T/U"
      }
    },
    {
      "id": "X29",
      "name": "Panoramic stimuli",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Presentation and action response",
      "bibkey": "Han2026PanoramicStimuli",
      "title": "Leveraging Generative AI for High-Fidelity 360degree Spatial Images: Methodological Validation for Use as Experimental Stimuli",
      "year": 2026,
      "venue": "Buildings",
      "authors": "Han, Yoojin and Jeong, Joowon",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.3390/buildings16091679",
      "doi": "10.3390/buildings16091679",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-xr.tex:74",
      "project_url": "",
      "url": "https://doi.org/10.3390/buildings16091679",
      "kind": "system",
      "input_tags": [
        "T",
        "I"
      ],
      "inputs": [
        "Text",
        "Image"
      ],
      "description": "Static panoramas · Quest 3 · Stimuli",
      "fields": {
        "Input": "Text, Image",
        "Model / component": "Skybox AI",
        "Artifact": "Static panoramas",
        "Platform": "Quest 3",
        "Task": "Stimuli",
        "Evaluation": "T/E"
      }
    },
    {
      "id": "X30",
      "name": "CinemaWorld",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Presentation and action response",
      "bibkey": "Ihara2026CinemaWorld",
      "title": "CinemaWorld: Generative Augmented Reality with LLMs and 3D Scene Generation for Movie Augmentation",
      "year": 2026,
      "venue": "arXiv",
      "authors": "Keiichi Ihara and DaeHo Lee and Manato Abe and Hye-Young Jo and Ryo Suzuki",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2603.08060v1",
      "doi": "10.48550/arXiv.2603.08060",
      "arxiv": "2603.08060",
      "source": "manuscript/tables/catalogue-xr.tex:75",
      "project_url": "https://hyeyoungjo.com/cinemaworld/",
      "url": "https://hyeyoungjo.com/cinemaworld/",
      "kind": "system",
      "input_tags": [
        "V",
        "G"
      ],
      "inputs": [
        "Video",
        "Geometry / scene context"
      ],
      "description": "Timed meshes /effects · Quest 3 /Unity · Film augmentation",
      "fields": {
        "Input": "Video, Geometry / scene context",
        "Model / component": "Gemini-2.5-pro /gpt-image-1 /InstantMesh",
        "Artifact": "Timed meshes /effects",
        "Platform": "Quest 3 /Unity",
        "Task": "Film augmentation",
        "Evaluation": "F/T/U/E"
      }
    },
    {
      "id": "X31",
      "name": "ShadAR",
      "category": "xr",
      "category_label": "XR systems",
      "group": "Presentation and action response",
      "bibkey": "Mei2026ShadAR",
      "title": "ShadAR: Real-time Prompting On-demand Visual Augmentation in Augmented Reality",
      "year": 2026,
      "venue": "arXiv",
      "authors": "Yanni Mei and Samuel Hartenstein and Jonas Wombacher and Florian Mueller and Jan Gugenheimer",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/2610.19998v1",
      "doi": "10.48550/arXiv.2610.19998",
      "arxiv": "2610.19998",
      "source": "manuscript/tables/catalogue-xr.tex:77",
      "project_url": "",
      "url": "https://arxiv.org/abs/2610.19998v1",
      "kind": "system",
      "input_tags": [
        "Sp",
        "I"
      ],
      "inputs": [
        "Speech",
        "Image"
      ],
      "description": "HLSL /altered passthrough · Quest 3 +RTX 5090 · Visual augmentation",
      "fields": {
        "Input": "Speech, Image",
        "Model / component": "GPT-5.2 /YOLO26 /Whisper",
        "Artifact": "HLSL /altered passthrough",
        "Platform": "Quest 3 +RTX 5090",
        "Task": "Visual augmentation",
        "Evaluation": "T/X"
      }
    },
    {
      "id": "R1",
      "name": "ShapeNet",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Chang2015ShapeNet",
      "title": "ShapeNet: An Information-Rich 3D Model Repository",
      "year": 2015,
      "venue": "arXiv",
      "authors": "Angel X. Chang and Thomas Funkhouser and Leonidas Guibas and Pat Hanrahan and Qixing Huang and Zimo Li and Silvio Savarese and Manolis Savva and Shuran Song and Hao Su and Jianxiong Xiao and Li Yi and Fisher Yu",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/1512.03012",
      "doi": "",
      "arxiv": "1512.03012",
      "source": "manuscript/tables/catalogue-resources.tex:25",
      "project_url": "",
      "url": "https://arxiv.org/abs/1512.03012",
      "kind": "resource",
      "description": "Dataset · assets · 220K classified models",
      "fields": {
        "Domain": "assets",
        "Origin": "Synthetic / simulated",
        "Signals": "Geometry / layout, Semantics / boxes",
        "Other signals": "—",
        "Reported scale": "220K classified models"
      }
    },
    {
      "id": "R2",
      "name": "Objaverse 1.0",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Deitke2023Objaverse",
      "title": "Objaverse: A Universe of Annotated 3D Objects",
      "year": 2023,
      "venue": "CVPR 2023",
      "authors": "Matt Deitke and Dustin Schwenk and Jordi Salvador and Luca Weihs and Oscar Michel and Eli VanderBilt and Ludwig Schmidt and Kiana Ehsani and Aniruddha Kembhavi and Ali Farhadi",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2212.08051",
      "doi": "10.1109/cvpr52729.2023.01263",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:26",
      "project_url": "",
      "url": "https://arxiv.org/abs/2212.08051",
      "kind": "resource",
      "description": "Dataset · assets · 800K+models",
      "fields": {
        "Domain": "assets",
        "Origin": "NR",
        "Signals": "Geometry / layout",
        "Other signals": "Text/Anim",
        "Reported scale": "800K+models"
      }
    },
    {
      "id": "R3",
      "name": "Objaverse-XL",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Deitke2023ObjaverseXL",
      "title": "Objaverse-XL: A Universe of 10M+ 3D Objects",
      "year": 2023,
      "venue": "NeurIPS 2023 Datasets and Benchmarks Track",
      "authors": "Matt Deitke and Ruoshi Liu and Matthew Wallingford and Huong Ngo and Oscar Michel and Aditya Kusupati and Alan Fan and Christian Laforte and Vikram Voleti and Samir Yitzhak Gadre and Eli VanderBilt and Aniruddha Kembhavi and Carl Vondrick and Georgia Gkioxari and Kiana Ehsani and Ludwig Schmidt and Ali Farhadi",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/70364304877b5e767de4e9a2a511be0c-Abstract-Datasets_and_Benchmarks.html",
      "doi": "10.52202/075280-1554",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:28",
      "project_url": "",
      "url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/70364304877b5e767de4e9a2a511be0c-Abstract-Datasets_and_Benchmarks.html",
      "kind": "resource",
      "description": "Dataset · assets · >10M objects",
      "fields": {
        "Domain": "assets",
        "Origin": "Mixed",
        "Signals": "Geometry / layout",
        "Other signals": "Meta.",
        "Reported scale": ">10M objects"
      }
    },
    {
      "id": "R4",
      "name": "ABO",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Collins2022ABO",
      "title": "ABO: Dataset and Benchmarks for Real-World 3D Object Understanding",
      "year": 2022,
      "venue": "CVPR 2022",
      "authors": "Jasmine Collins and Shubham Goel and Kenan Deng and Achleshwar Luthra and Leon Xu and Erhan Gundogdu and Xi Zhang and Yago Vicente, Tomas F. and Thomas Dideriksen and Himanshu Arora and Matthieu Guillaumin and Jitendra Malik",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2110.06199",
      "doi": "10.1109/cvpr52688.2022.02045",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:29",
      "project_url": "",
      "url": "https://arxiv.org/abs/2110.06199",
      "kind": "resource",
      "description": "Dataset · assets · NR",
      "fields": {
        "Domain": "assets",
        "Origin": "Mixed",
        "Signals": "RGB, Geometry / layout",
        "Other signals": "Meta.",
        "Reported scale": "NR"
      }
    },
    {
      "id": "R5",
      "name": "Google Scanned Objects",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Downs2022GSO",
      "title": "Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items",
      "year": 2022,
      "venue": "2022 International Conference on Robotics and Automation (ICRA)",
      "authors": "Downs, Laura and Francis, Anthony and Koenig, Nate and Kinman, Brandon and Hickman, Ryan and Reymann, Krista and McHugh, Thomas B. and Vanhoucke, Vincent",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2204.11918",
      "doi": "10.1109/icra46639.2022.9811809",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:31",
      "project_url": "",
      "url": "https://arxiv.org/abs/2204.11918",
      "kind": "resource",
      "description": "Dataset · assets · >1,000 objects",
      "fields": {
        "Domain": "assets",
        "Origin": "Real capture",
        "Signals": "Geometry / layout",
        "Other signals": "Tex.",
        "Reported scale": ">1,000 objects"
      }
    },
    {
      "id": "R6",
      "name": "3D-FRONT",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Fu2021ThreeDFRONT",
      "title": "3D-FRONT: 3D Furnished Rooms With layOuts and semaNTics",
      "year": 2021,
      "venue": "ICCV 2021",
      "authors": "Huan Fu and Bowen Cai and Lin Gao and Ling-Xiao Zhang and Jiaming Wang and Cao Li and Qixun Zeng and Chengyue Sun and Rongfei Jia and Binqiang Zhao and Hao Zhang",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/ICCV2021/html/Fu_3D-FRONT_3D_Furnished_Rooms_With_layOuts_and_semaNTics_ICCV_2021_paper.html",
      "doi": "10.1109/iccv48922.2021.01075",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:32",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/ICCV2021/html/Fu_3D-FRONT_3D_Furnished_Rooms_With_layOuts_and_semaNTics_ICCV_2021_paper.html",
      "kind": "resource",
      "description": "Dataset · scenes · 18,968 rooms",
      "fields": {
        "Domain": "scenes",
        "Origin": "Synthetic / simulated",
        "Signals": "Geometry / layout, Semantics / boxes",
        "Other signals": "Tex.",
        "Reported scale": "18,968 rooms"
      }
    },
    {
      "id": "R7",
      "name": "SUN RGB-D",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Song2015SUNRGBD",
      "title": "SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite",
      "year": 2015,
      "venue": "Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition",
      "authors": "Song, Shuran and Lichtenberg, Samuel P. and Xiao, Jianxiong",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content_cvpr_2015/html/Song_SUN_RGB-D_A_2015_CVPR_paper.html",
      "doi": "10.1109/cvpr.2015.7298655",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:34",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content_cvpr_2015/html/Song_SUN_RGB-D_A_2015_CVPR_paper.html",
      "kind": "resource",
      "description": "Dataset · scenes · 10,335 images",
      "fields": {
        "Domain": "scenes",
        "Origin": "Real capture",
        "Signals": "RGB, Depth, Semantics / boxes",
        "Other signals": "—",
        "Reported scale": "10,335 images"
      }
    },
    {
      "id": "R8",
      "name": "S3DIS",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Armeni2016S3DIS",
      "title": "3D Semantic Parsing of Large-Scale Indoor Spaces",
      "year": 2016,
      "venue": "Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition",
      "authors": "Armeni, Iro and Sener, Ozan and Zamir, Amir R. and Jiang, Helen and Brilakis, Ioannis and Fischer, Martin and Savarese, Silvio",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content_cvpr_2016/html/Armeni_3D_Semantic_Parsing_CVPR_2016_paper.html",
      "doi": "10.1109/cvpr.2016.170",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:35",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content_cvpr_2016/html/Armeni_3D_Semantic_Parsing_CVPR_2016_paper.html",
      "kind": "resource",
      "description": "Dataset · scenes · >6,000 m²",
      "fields": {
        "Domain": "scenes",
        "Origin": "Real capture",
        "Signals": "Geometry / layout, Semantics / boxes",
        "Other signals": "—",
        "Reported scale": ">6,000 m²"
      }
    },
    {
      "id": "R9",
      "name": "ScanNet",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Dai2017ScanNet",
      "title": "ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes",
      "year": 2017,
      "venue": "Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition",
      "authors": "Dai, Angela and Chang, Angel X. and Savva, Manolis and Halber, Maciej and Funkhouser, Thomas and Niessner, Matthias",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content_cvpr_2017/html/Dai_ScanNet_Richly-Annotated_3D_CVPR_2017_paper.html",
      "doi": "10.1109/cvpr.2017.261",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:37",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content_cvpr_2017/html/Dai_ScanNet_Richly-Annotated_3D_CVPR_2017_paper.html",
      "kind": "resource",
      "description": "Dataset · scenes · 1,513 scenes",
      "fields": {
        "Domain": "scenes",
        "Origin": "Real capture",
        "Signals": "RGB, Depth, Pose, Geometry / layout, Semantics / boxes",
        "Other signals": "—",
        "Reported scale": "1,513 scenes"
      }
    },
    {
      "id": "R10",
      "name": "Matterport3D",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Chang2017Matterport3D",
      "title": "Matterport3D: Learning from RGB-D Data in Indoor Environments",
      "year": 2017,
      "venue": "2017 International Conference on 3D Vision (3DV)",
      "authors": "Chang, Angel and Dai, Angela and Funkhouser, Thomas and Halber, Maciej and Nießner, Matthias and Savva, Manolis and Song, Shuran and Zeng, Andy and Zhang, Yinda",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/1709.06158",
      "doi": "10.1109/3dv.2017.00081",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:38",
      "project_url": "",
      "url": "https://arxiv.org/abs/1709.06158",
      "kind": "resource",
      "description": "Dataset · scenes · 90 buildings",
      "fields": {
        "Domain": "scenes",
        "Origin": "Real capture",
        "Signals": "RGB, Depth, Pose, Geometry / layout, Semantics / boxes",
        "Other signals": "—",
        "Reported scale": "90 buildings"
      }
    },
    {
      "id": "R11",
      "name": "Replica",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Straub2019Replica",
      "title": "The Replica Dataset: A Digital Replica of Indoor Spaces",
      "year": 2019,
      "venue": "arXiv",
      "authors": "Straub, Julian and Whelan, Thomas and Ma, Lingni and Chen, Yufan and Wijmans, Erik and Green, Simon and Engel, Jakob J. and Mur-Artal, Raul and Ren, Carl and Verma, Shobhit and Clarkson, Anton and Yan, Mingfei and Budge, Brian and Yan, Yajie and Pan, Xiaqing and Yon, June and Zou, Yuyang and Leon, Kimberly and Carter, Nigel and Briales, Jesus and Gillingham, Tyler and Mueggler, Elias and Pesqueira, Luis and Savva, Manolis and Batra, Dhruv and Strasdat, Hauke M. and De Nardi, Renzo and Goesele, Michael and Lovegrove, Steven and Newcombe, Richard",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/1906.05797",
      "doi": "",
      "arxiv": "1906.05797",
      "source": "manuscript/tables/catalogue-resources.tex:40",
      "project_url": "",
      "url": "https://arxiv.org/abs/1906.05797",
      "kind": "resource",
      "description": "Dataset · scenes · 18 reconstructions",
      "fields": {
        "Domain": "scenes",
        "Origin": "Real capture",
        "Signals": "Geometry / layout, Semantics / boxes",
        "Other signals": "Tex.",
        "Reported scale": "18 reconstructions"
      }
    },
    {
      "id": "R12",
      "name": "ScanNet++",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Yeshwanth2023ScanNetPP",
      "title": "ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes",
      "year": 2023,
      "venue": "Proceedings of the IEEE/CVF International Conference on Computer Vision",
      "authors": "Yeshwanth, Chandan and Liu, Yueh-Cheng and Nießner, Matthias and Dai, Angela",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/ICCV2023/html/Yeshwanth_ScanNet_A_High-Fidelity_Dataset_of_3D_Indoor_Scenes_ICCV_2023_paper.html",
      "doi": "10.1109/iccv51070.2023.00008",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:41",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/ICCV2023/html/Yeshwanth_ScanNet_A_High-Fidelity_Dataset_of_3D_Indoor_Scenes_ICCV_2023_paper.html",
      "kind": "resource",
      "description": "Dataset · scenes · 460 scenes",
      "fields": {
        "Domain": "scenes",
        "Origin": "Real capture",
        "Signals": "RGB, Depth, Geometry / layout, Semantics / boxes",
        "Other signals": "—",
        "Reported scale": "460 scenes"
      }
    },
    {
      "id": "R13",
      "name": "ARKitScenes",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Baruch2021ARKitScenes",
      "title": "ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data",
      "year": 2021,
      "venue": "Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks",
      "authors": "Baruch, Gilad and Chen, Zhuoyuan and Dehghan, Afshin and Dimry, Tal and Feigin, Yuri and Fu, Peter and Gebauer, Thomas and Joffe, Brandon and Kurz, Daniel and Schwartz, Arik and Shulman, Elad",
      "publication_type": "venue_publication",
      "paper_url": "https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/66f041e16a60928b05a7e228a89c3799-Abstract-round1.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:43",
      "project_url": "",
      "url": "https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/66f041e16a60928b05a7e228a89c3799-Abstract-round1.html",
      "kind": "resource",
      "description": "Dataset · scenes · NR",
      "fields": {
        "Domain": "scenes",
        "Origin": "Real capture",
        "Signals": "RGB, Depth, Semantics / boxes",
        "Other signals": "—",
        "Reported scale": "NR"
      }
    },
    {
      "id": "R14",
      "name": "HM3D",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Ramakrishnan2021HM3D",
      "title": "Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI",
      "year": 2021,
      "venue": "Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks",
      "authors": "Ramakrishnan, Santhosh Kumar and Gokaslan, Aaron and Wijmans, Erik and Maksymets, Oleksandr and Clegg, Alexander and Turner, John and Undersander, Eric and Galuba, Wojciech and Westbury, Andrew and Chang, Angel and Savva, Manolis and Zhao, Yili and Batra, Dhruv",
      "publication_type": "venue_publication",
      "paper_url": "https://datasets-benchmarks-proceedings.neurips.cc/paper_files/paper/2021/hash/34173cb38f07f89ddbebc2ac9128303f-Abstract-round2.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:44",
      "project_url": "",
      "url": "https://datasets-benchmarks-proceedings.neurips.cc/paper_files/paper/2021/hash/34173cb38f07f89ddbebc2ac9128303f-Abstract-round2.html",
      "kind": "resource",
      "description": "Dataset · scenes · 1,000 reconstructions",
      "fields": {
        "Domain": "scenes",
        "Origin": "Real capture",
        "Signals": "Geometry / layout",
        "Other signals": "Tex.",
        "Reported scale": "1,000 reconstructions"
      }
    },
    {
      "id": "R15",
      "name": "DL3DV-10K",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Ling2024DL3DV",
      "title": "DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision",
      "year": 2024,
      "venue": "CVPR 2024",
      "authors": "Lu Ling and Yichen Sheng and Zhi Tu and Wentian Zhao and Cheng Xin and Kun Wan and Lantao Yu and Qianyu Guo and Zixun Yu and Yawen Lu and Xuanmao Li and Xingpeng Sun and Rohan Ashok and Aniruddha Mukherjee and Hao Kang and Xiangrui Kong and Gang Hua and Tianyi Zhang and Bedrich Benes and Aniket Bera",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Ling_DL3DV-10K_A_Large-Scale_Scene_Dataset_for_Deep_Learning-based_3D_Vision_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.02092",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:46",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Ling_DL3DV-10K_A_Large-Scale_Scene_Dataset_for_Deep_Learning-based_3D_Vision_CVPR_2024_paper.html",
      "kind": "resource",
      "description": "Dataset · video · NR",
      "fields": {
        "Domain": "video",
        "Origin": "Real capture",
        "Signals": "RGB",
        "Other signals": "—",
        "Reported scale": "NR"
      }
    },
    {
      "id": "R16",
      "name": "RealEstate10K",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Zhou2018StereoMagnification",
      "title": "Stereo Magnification: Learning View Synthesis Using Multiplane Images",
      "year": 2018,
      "venue": "ACM Transactions on Graphics",
      "authors": "Tinghui Zhou and Richard Tucker and John Flynn and Graham Fyffe and Noah Snavely",
      "publication_type": "venue_publication",
      "paper_url": "https://research.google/pubs/stereo-magnification-learning-view-synthesis-using-multiplane-images/",
      "doi": "10.1145/3197517.3201323",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:47",
      "project_url": "",
      "url": "https://research.google/pubs/stereo-magnification-learning-view-synthesis-using-multiplane-images/",
      "kind": "resource",
      "description": "Dataset · video · ≈80,000 clips",
      "fields": {
        "Domain": "video",
        "Origin": "Real capture",
        "Signals": "RGB, Pose",
        "Other signals": "—",
        "Reported scale": "≈80,000 clips"
      }
    },
    {
      "id": "R17",
      "name": "CO3D",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Reizenstein2021CO3D",
      "title": "Common Objects in 3D: Large-Scale Learning and Evaluation of Real-Life 3D Category Reconstruction",
      "year": 2021,
      "venue": "Proceedings of the IEEE/CVF International Conference on Computer Vision",
      "authors": "Reizenstein, Jeremy and Shapovalov, Roman and Henzler, Philipp and Sbordone, Luca and Labatut, Patrick and Novotny, David",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/ICCV2021/html/Reizenstein_Common_Objects_in_3D_Large-Scale_Learning_and_Evaluation_of_Real-Life_ICCV_2021_paper.html",
      "doi": "10.1109/iccv48922.2021.01072",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:49",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/ICCV2021/html/Reizenstein_Common_Objects_in_3D_Large-Scale_Learning_and_Evaluation_of_Real-Life_ICCV_2021_paper.html",
      "kind": "resource",
      "description": "Dataset · assets · ≈19,000 videos",
      "fields": {
        "Domain": "assets",
        "Origin": "Real capture",
        "Signals": "RGB, Pose, Geometry / layout",
        "Other signals": "—",
        "Reported scale": "≈19,000 videos"
      }
    },
    {
      "id": "R18",
      "name": "Ego4D",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Grauman2022Ego4D",
      "title": "Ego4D: Around the World in 3,000 Hours of Egocentric Video",
      "year": 2022,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Grauman, Kristen and Westbury, Andrew and Byrne, Eugene and Chavis, Zachary and Furnari, Antonino and Girdhar, Rohit and Hamburger, Jackson and Jiang, Hao and Liu, Miao and Liu, Xingyu and Martin, Miguel and Nagarajan, Tushar and Radosavovic, Ilija and Ramakrishnan, Santhosh Kumar and Ryan, Fiona and Sharma, Jayant and Wray, Michael and Xu, Mengmeng and Xu, Eric Zhongcong and Zhao, Chen and Bansal, Siddhant and Batra, Dhruv and Cartillier, Vincent and Crane, Sean and Do, Tien and Doulaty, Morrie and Erapalli, Akshay and Feichtenhofer, Christoph and Fragomeni, Adriano and Fu, Qichen and Gebreselasie, Abrham and González, Cristina and Hillis, James and Huang, Xuhua and Huang, Yifei and Jia, Wenqi and Khoo, Weslie and Kolář, Jáchym and Kottur, Satwik and Kumar, Anurag and Landini, Federico and Li, Chao and Li, Yanghao and Li, Zhenqiang and Mangalam, Karttikeya and Modhugu, Raghava and Munro, Jonathan and Murrell, Tullie and Nishiyasu, Takumi and Price, Will and Ruiz, Paola and Ramazanova, Merey and Sari, Leda and Somasundaram, Kiran and Southerland, Audrey and Sugano, Yusuke and Tao, Ruijie and Vo, Minh and Wang, Yuchen and Wu, Xindi and Yagi, Takuma and Zhao, Ziwei and Zhu, Yunyi and Arbeláez, Pablo and Crandall, David and Damen, Dima and Farinella, Giovanni Maria and Fuegen, Christian and Ghanem, Bernard and Ithapu, Vamsi Krishna and Jawahar, C. V. and Joo, Hanbyul and Kitani, Kris and Li, Haizhou and Newcombe, Richard and Oliva, Aude and Park, Hyun Soo and Rehg, James M. and Sato, Yoichi and Shi, Jianbo and Shou, Mike Zheng and Torralba, Antonio and Torresani, Lorenzo and Yan, Mingfei and Malik, Jitendra",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2022/html/Grauman_Ego4D_Around_the_World_in_3000_Hours_of_Egocentric_Video_CVPR_2022_paper.html",
      "doi": "10.1109/cvpr52688.2022.01842",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:50",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2022/html/Grauman_Ego4D_Around_the_World_in_3000_Hours_of_Egocentric_Video_CVPR_2022_paper.html",
      "kind": "resource",
      "description": "Dataset · actions · 3,670 hours",
      "fields": {
        "Domain": "actions",
        "Origin": "Real capture",
        "Signals": "RGB, Actions",
        "Other signals": "—",
        "Reported scale": "3,670 hours"
      }
    },
    {
      "id": "R19",
      "name": "Ego-Exo4D",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Grauman2024EgoExo4D",
      "title": "Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives",
      "year": 2024,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Grauman, Kristen and Westbury, Andrew and Torresani, Lorenzo and Kitani, Kris and Malik, Jitendra and Afouras, Triantafyllos and Ashutosh, Kumar and Baiyya, Vijay and Bansal, Siddhant and Boote, Bikram and Byrne, Eugene and Chavis, Zach and Chen, Joya and Cheng, Feng and Chu, Fu-Jen and Crane, Sean and Dasgupta, Avijit and Dong, Jing and Escobar, Maria and Forigua, Cristhian and Gebreselasie, Abrham and Haresh, Sanjay and Huang, Jing and Islam, Md Mohaiminul and Jain, Suyog and Khirodkar, Rawal and Kukreja, Devansh and Liang, Kevin J and Liu, Jia-Wei and Majumder, Sagnik and Mao, Yongsen and Martin, Miguel and Mavroudi, Effrosyni and Nagarajan, Tushar and Ragusa, Francesco and Ramakrishnan, Santhosh Kumar and Seminara, Luigi and Somayazulu, Arjun and Song, Yale and Su, Shan and Xue, Zihui and Zhang, Edward and Zhang, Jinxu and Castillo, Angela and Chen, Changan and Fu, Xinzhu and Furuta, Ryosuke and Gonzalez, Cristina and Gupta, Prince and Hu, Jiabo and Huang, Yifei and Huang, Yiming and Khoo, Weslie and Kumar, Anush and Kuo, Robert and Lakhavani, Sach and Liu, Miao and Luo, Mi and Luo, Zhengyi and Meredith, Brighid and Miller, Austin and Oguntola, Oluwatumininu and Pan, Xiaqing and Peng, Penny and Pramanick, Shraman and Ramazanova, Merey and Ryan, Fiona and Shan, Wei and Somasundaram, Kiran and Song, Chenan and Southerland, Audrey and Tateno, Masatoshi and Wang, Huiyu and Wang, Yuchen and Yagi, Takuma and Yan, Mingfei and Yang, Xitong and Yu, Zecheng and Zha, Shengxin Cindy and Zhao, Chen and Zhao, Ziwei and Zhu, Zhifan and Zhuo, Jeff and Arbelaez, Pablo and Bertasius, Gedas and Damen, Dima and Engel, Jakob and Farinella, Giovanni Maria and Furnari, Antonino and Ghanem, Bernard and Hoffman, Judy and Jawahar, C.V. and Newcombe, Richard and Park, Hyun Soo and Rehg, James M. and Sato, Yoichi and Savva, Manolis and Shi, Jianbo and Shou, Mike Zheng and Wray, Michael",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Grauman_Ego-Exo4D_Understanding_Skilled_Human_Activity_from_First-_and_Third-Person_Perspectives_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.01834",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:52",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Grauman_Ego-Exo4D_Understanding_Skilled_Human_Activity_from_First-_and_Third-Person_Perspectives_CVPR_2024_paper.html",
      "kind": "resource",
      "description": "Dataset · actions · 1,286 hours",
      "fields": {
        "Domain": "actions",
        "Origin": "Real capture",
        "Signals": "RGB, Pose, Actions",
        "Other signals": "IMU",
        "Reported scale": "1,286 hours"
      }
    },
    {
      "id": "R20",
      "name": "HOT3D",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Banerjee2025HOT3D",
      "title": "HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos",
      "year": 2025,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Banerjee, Prithviraj and Shkodrani, Sindi and Moulon, Pierre and Hampali, Shreyas and Han, Shangchen and Zhang, Fan and Zhang, Linguang and Fountain, Jade and Miller, Edward and Basol, Selen and Newcombe, Richard and Wang, Robert and Engel, Jakob Julian and Hodan, Tomas",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2025/html/Banerjee_HOT3D_Hand_and_Object_Tracking_in_3D_from_Egocentric_Multi-View_CVPR_2025_paper.html",
      "doi": "10.1109/CVPR52734.2025.00662",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:53",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2025/html/Banerjee_HOT3D_Hand_and_Object_Tracking_in_3D_from_Egocentric_Multi-View_CVPR_2025_paper.html",
      "kind": "resource",
      "description": "Dataset · actions · NR",
      "fields": {
        "Domain": "actions",
        "Origin": "Real capture",
        "Signals": "RGB, Pose",
        "Other signals": "—",
        "Reported scale": "NR"
      }
    },
    {
      "id": "R21",
      "name": "SCOPE",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Dataset",
      "bibkey": "Tamir2025Stereoscopic",
      "title": "What Makes for a Good Stereoscopic Image?",
      "year": 2025,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops",
      "authors": "Netanel Y. Tamir and Shir Amir and Ranel Itzhaky and Noam Atia and Shobhita Sundaram and Stephanie Fu and Ron Sokolovsky and Phillip Isola and Tali Dekel and Richard Zhang and Miriam Farber",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2025W/CV4Metaverse/html/Tamir_What_Makes_for_a_Good_Stereoscopic_Image_CVPRW_2025_paper.html",
      "doi": "10.1109/cvprw67362.2025.00031",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:55",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2025W/CV4Metaverse/html/Tamir_What_Makes_for_a_Good_Stereoscopic_Image_CVPRW_2025_paper.html",
      "kind": "resource",
      "description": "Dataset · scenes · 2,400 samples",
      "fields": {
        "Domain": "scenes",
        "Origin": "Mixed",
        "Signals": "No selected signal listed",
        "Other signals": "Stereo/Pref.",
        "Reported scale": "2,400 samples"
      }
    },
    {
      "id": "R22",
      "name": "Habitat",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Simulator",
      "bibkey": "Savva2019Habitat",
      "title": "Habitat: A Platform for Embodied AI Research",
      "year": 2019,
      "venue": "Proceedings of the IEEE/CVF International Conference on Computer Vision",
      "authors": "Savva, Manolis and Kadian, Abhishek and Maksymets, Oleksandr and Zhao, Yili and Wijmans, Erik and Jain, Bhavana and Straub, Julian and Liu, Jia and Koltun, Vladlen and Malik, Jitendra and Parikh, Devi and Batra, Dhruv",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content_ICCV_2019/html/Savva_Habitat_A_Platform_for_Embodied_AI_Research_ICCV_2019_paper.html",
      "doi": "10.1109/iccv.2019.00943",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:57",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content_ICCV_2019/html/Savva_Habitat_A_Platform_for_Embodied_AI_Research_ICCV_2019_paper.html",
      "kind": "resource",
      "description": "Simulator · scenes · NR",
      "fields": {
        "Domain": "scenes",
        "Origin": "Synthetic / simulated",
        "Signals": "RGB, Depth, Actions",
        "Other signals": "—",
        "Reported scale": "NR"
      }
    },
    {
      "id": "R23",
      "name": "Gibson",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Simulator",
      "bibkey": "Xia2018Gibson",
      "title": "Gibson Env: Real-World Perception for Embodied Agents",
      "year": 2018,
      "venue": "Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition",
      "authors": "Xia, Fei and Zamir, Amir R. and He, Zhiyang and Sax, Alexander and Malik, Jitendra and Savarese, Silvio",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content_cvpr_2018/html/Xia_Gibson_Env_Real-World_CVPR_2018_paper.html",
      "doi": "10.1109/cvpr.2018.00945",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:59",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content_cvpr_2018/html/Xia_Gibson_Env_Real-World_CVPR_2018_paper.html",
      "kind": "resource",
      "description": "Simulator · scenes · 572 buildings",
      "fields": {
        "Domain": "scenes",
        "Origin": "Synthetic / simulated",
        "Signals": "RGB, Geometry / layout, Actions",
        "Other signals": "—",
        "Reported scale": "572 buildings"
      }
    },
    {
      "id": "R24",
      "name": "AI2-THOR",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Simulator",
      "bibkey": "Kolve2017AI2THOR",
      "title": "AI2-THOR: An Interactive 3D Environment for Visual AI",
      "year": 2017,
      "venue": "arXiv",
      "authors": "Kolve, Eric and Mottaghi, Roozbeh and Gordon, Daniel and Zhu, Yuke and Gupta, Abhinav and Farhadi, Ali",
      "publication_type": "preprint_record",
      "paper_url": "https://arxiv.org/abs/1712.05474v1",
      "doi": "",
      "arxiv": "1712.05474",
      "source": "manuscript/tables/catalogue-resources.tex:60",
      "project_url": "",
      "url": "https://arxiv.org/abs/1712.05474v1",
      "kind": "resource",
      "description": "Simulator · actions · NR",
      "fields": {
        "Domain": "actions",
        "Origin": "Synthetic / simulated",
        "Signals": "RGB, Actions",
        "Other signals": "State",
        "Reported scale": "NR"
      }
    },
    {
      "id": "R25",
      "name": "ProcTHOR",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Simulator",
      "bibkey": "Deitke2022ProcTHOR",
      "title": "ProcTHOR: Large-Scale Embodied AI Using Procedural Generation",
      "year": 2022,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Deitke, Matt and VanderBilt, Eli and Herrasti, Alvaro and Weihs, Luca and Ehsani, Kiana and Salvador, Jordi and Han, Winson and Kolve, Eric and Kembhavi, Aniruddha and Mottaghi, Roozbeh",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper_files/paper/2022/hash/27c546ab1e4f1d7d638e6a8dfbad9a07-Abstract-Conference.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:62",
      "project_url": "",
      "url": "https://proceedings.neurips.cc/paper_files/paper/2022/hash/27c546ab1e4f1d7d638e6a8dfbad9a07-Abstract-Conference.html",
      "kind": "resource",
      "description": "Simulator · scenes · 10,000 sampled houses",
      "fields": {
        "Domain": "scenes",
        "Origin": "Synthetic / simulated",
        "Signals": "RGB, Geometry / layout, Actions",
        "Other signals": "—",
        "Reported scale": "10,000 sampled houses"
      }
    },
    {
      "id": "R26",
      "name": "SAPIEN",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Simulator",
      "bibkey": "Xiang2020SAPIEN",
      "title": "SAPIEN: A SimulAted Part-Based Interactive ENvironment",
      "year": 2020,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Xiang, Fanbo and Qin, Yuzhe and Mo, Kaichun and Xia, Yikuan and Zhu, Hao and Liu, Fangchen and Liu, Minghua and Jiang, Hanxiao and Yuan, Yifu and Wang, He and Yi, Li and Chang, Angel X. and Guibas, Leonidas J. and Su, Hao",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content_CVPR_2020/html/Xiang_SAPIEN_A_SimulAted_Part-Based_Interactive_ENvironment_CVPR_2020_paper.html",
      "doi": "10.1109/cvpr42600.2020.01111",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:63",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content_CVPR_2020/html/Xiang_SAPIEN_A_SimulAted_Part-Based_Interactive_ENvironment_CVPR_2020_paper.html",
      "kind": "resource",
      "description": "Simulator · actions · NR",
      "fields": {
        "Domain": "actions",
        "Origin": "Synthetic / simulated",
        "Signals": "Geometry / layout, Actions",
        "Other signals": "Phys.",
        "Reported scale": "NR"
      }
    },
    {
      "id": "R27",
      "name": "Habitat 2.0",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Simulator",
      "bibkey": "Szot2021Habitat2",
      "title": "Habitat 2.0: Training Home Assistants to Rearrange their Habitat",
      "year": 2021,
      "venue": "Advances in Neural Information Processing Systems",
      "authors": "Szot, Andrew and Clegg, Alexander and Undersander, Eric and Wijmans, Erik and Zhao, Yili and Turner, John and Maestre, Noah and Mukadam, Mustafa and Chaplot, Devendra Singh and Maksymets, Oleksandr and Gokaslan, Aaron and Vondruš, Vladimír and Dharur, Sameer and Meier, Franziska and Galuba, Wojciech and Chang, Angel and Kira, Zsolt and Koltun, Vladlen and Malik, Jitendra and Savva, Manolis and Batra, Dhruv",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.neurips.cc/paper_files/paper/2021/hash/021bbc7ee20b71134d53e20206bd6feb-Abstract.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:65",
      "project_url": "",
      "url": "https://proceedings.neurips.cc/paper_files/paper/2021/hash/021bbc7ee20b71134d53e20206bd6feb-Abstract.html",
      "kind": "resource",
      "description": "Simulator · actions · NR",
      "fields": {
        "Domain": "actions",
        "Origin": "Synthetic / simulated",
        "Signals": "RGB, Actions",
        "Other signals": "Phys.",
        "Reported scale": "NR"
      }
    },
    {
      "id": "R28",
      "name": "iGibson 1.0",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Simulator",
      "bibkey": "Shen2021iGibson",
      "title": "iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes",
      "year": 2021,
      "venue": "2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
      "authors": "Shen, Bokui and Xia, Fei and Li, Chengshu and Martin-Martin, Roberto and Fan, Linxi and Wang, Guanzhi and Perez-D'Arpino, Claudia and Buch, Shyamal and Srivastava, Sanjana and Tchapmi, Lyne and Tchapmi, Micael and Vainio, Kent and Wong, Josiah and Fei-Fei, Li and Savarese, Silvio",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2012.02924",
      "doi": "10.1109/iros51168.2021.9636667",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:66",
      "project_url": "",
      "url": "https://arxiv.org/abs/2012.02924",
      "kind": "resource",
      "description": "Simulator · actions · 15 home scenes",
      "fields": {
        "Domain": "actions",
        "Origin": "Synthetic / simulated",
        "Signals": "RGB, Depth, Semantics / boxes, Actions",
        "Other signals": "—",
        "Reported scale": "15 home scenes"
      }
    },
    {
      "id": "R29",
      "name": "iGibson 2.0",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Simulator",
      "bibkey": "Li2022iGibson2",
      "title": "iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks",
      "year": 2022,
      "venue": "Conference on Robot Learning",
      "authors": "Li, Chengshu and Xia, Fei and Martín-Martín, Roberto and Lingelbach, Michael and Srivastava, Sanjana and Shen, Bokui and Vainio, Kent Elliott and Gokmen, Cem and Dharan, Gokul and Jain, Tanish and Kurenkov, Andrey and Liu, Karen and Gweon, Hyowon and Wu, Jiajun and Fei-Fei, Li and Savarese, Silvio",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.mlr.press/v164/li22b.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:68",
      "project_url": "",
      "url": "https://proceedings.mlr.press/v164/li22b.html",
      "kind": "resource",
      "description": "Simulator · actions · NR",
      "fields": {
        "Domain": "actions",
        "Origin": "Synthetic / simulated",
        "Signals": "Actions",
        "Other signals": "State/Demo.",
        "Reported scale": "NR"
      }
    },
    {
      "id": "R30",
      "name": "RoboTHOR",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Simulator",
      "bibkey": "Deitke2020RoboTHOR",
      "title": "RoboTHOR: An Open Simulation-to-Real Embodied AI Platform",
      "year": 2020,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
      "authors": "Deitke, Matt and Han, Winson and Herrasti, Alvaro and Kembhavi, Aniruddha and Kolve, Eric and Mottaghi, Roozbeh and Salvador, Jordi and Schwenk, Dustin and VanderBilt, Eli and Wallingford, Matthew and Weihs, Luca and Yatskar, Mark and Farhadi, Ali",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content_CVPR_2020/html/Deitke_RoboTHOR_An_Open_Simulation-to-Real_Embodied_AI_Platform_CVPR_2020_paper.html",
      "doi": "10.1109/cvpr42600.2020.00323",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:69",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content_CVPR_2020/html/Deitke_RoboTHOR_An_Open_Simulation-to-Real_Embodied_AI_Platform_CVPR_2020_paper.html",
      "kind": "resource",
      "description": "Simulator · actions · NR",
      "fields": {
        "Domain": "actions",
        "Origin": "Mixed",
        "Signals": "RGB, Actions",
        "Other signals": "—",
        "Reported scale": "NR"
      }
    },
    {
      "id": "R31",
      "name": "BEHAVIOR",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Benchmark",
      "bibkey": "Srivastava2022BEHAVIOR",
      "title": "BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments",
      "year": 2022,
      "venue": "Conference on Robot Learning",
      "authors": "Srivastava, Sanjana and Li, Chengshu and Lingelbach, Michael and Martín-Martín, Roberto and Xia, Fei and Vainio, Kent Elliott and Lian, Zheng and Gokmen, Cem and Buch, Shyamal and Liu, Karen and Savarese, Silvio and Gweon, Hyowon and Wu, Jiajun and Fei-Fei, Li",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.mlr.press/v164/srivastava22a.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:72",
      "project_url": "",
      "url": "https://proceedings.mlr.press/v164/srivastava22a.html",
      "kind": "resource",
      "description": "Benchmark · actions · 100 activities",
      "fields": {
        "Domain": "actions",
        "Origin": "Synthetic / simulated",
        "Signals": "Actions",
        "Other signals": "Goal/State/Demo.",
        "Reported scale": "100 activities"
      }
    },
    {
      "id": "R32",
      "name": "BEHAVIOR-1K",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Benchmark",
      "bibkey": "Li2023BEHAVIOR1K",
      "title": "BEHAVIOR-1K: A Benchmark for Embodied AI with 1,000 Everyday Activities and Realistic Simulation",
      "year": 2023,
      "venue": "Conference on Robot Learning",
      "authors": "Li, Chengshu and Zhang, Ruohan and Wong, Josiah and Gokmen, Cem and Srivastava, Sanjana and Martín-Martín, Roberto and Wang, Chen and Levine, Gabrael and Lingelbach, Michael and Sun, Jiankai and Anvari, Mona and Hwang, Minjune and Sharma, Manasi and Aydin, Arman and Bansal, Dhruva and Hunter, Samuel and Kim, Kyu-Young and Lou, Alan and Matthews, Caleb R and Villa-Renteria, Ivan and Tang, Jerry Huayang and Tang, Claire and Xia, Fei and Savarese, Silvio and Gweon, Hyowon and Liu, Karen and Wu, Jiajun and Fei-Fei, Li",
      "publication_type": "venue_publication",
      "paper_url": "https://proceedings.mlr.press/v205/li23a.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:73",
      "project_url": "",
      "url": "https://proceedings.mlr.press/v205/li23a.html",
      "kind": "resource",
      "description": "Benchmark · actions · 1,000 activities",
      "fields": {
        "Domain": "actions",
        "Origin": "Synthetic / simulated",
        "Signals": "Actions",
        "Other signals": "Goal/State/Phys.",
        "Reported scale": "1,000 activities"
      }
    },
    {
      "id": "R33",
      "name": "ManiSkill2",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Benchmark",
      "bibkey": "Gu2023ManiSkill2",
      "title": "ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills",
      "year": 2023,
      "venue": "International Conference on Learning Representations",
      "authors": "Gu, Jiayuan and Xiang, Fanbo and Li, Xuanlin and Ling, Zhan and Liu, Xiqiang and Mu, Tongzhou and Tang, Yihe and Tao, Stone and Wei, Xinyue and Yao, Yunchao and Yuan, Xiaodi and Xie, Pengwei and Huang, Zhiao and Chen, Rui and Su, Hao",
      "publication_type": "venue_publication",
      "paper_url": "https://arxiv.org/abs/2302.04659",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:75",
      "project_url": "",
      "url": "https://arxiv.org/abs/2302.04659",
      "kind": "resource",
      "description": "Benchmark · actions · 20 task families",
      "fields": {
        "Domain": "actions",
        "Origin": "Synthetic / simulated",
        "Signals": "RGB, Depth, Geometry / layout, Actions",
        "Other signals": "—",
        "Reported scale": "20 task families"
      }
    },
    {
      "id": "R34",
      "name": "NoveltyTHOR",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Benchmark",
      "bibkey": "Yang2024Holodeck",
      "title": "Holodeck: Language Guided Generation of 3D Embodied AI Environments",
      "year": 2024,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
      "authors": "Yue Yang and Fan-Yun Sun and Luca Weihs and Eli VanderBilt and Alvaro Herrasti and Winson Han and Jiajun Wu and Nick Haber and Ranjay Krishna and Lingjie Liu and Chris Callison-Burch and Mark Yatskar and Aniruddha Kembhavi and Christopher Clark",
      "publication_type": "venue_publication",
      "paper_url": "https://doi.org/10.1109/cvpr52733.2024.01536",
      "doi": "10.1109/cvpr52733.2024.01536",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:76",
      "project_url": "",
      "url": "https://doi.org/10.1109/cvpr52733.2024.01536",
      "kind": "resource",
      "description": "Benchmark · scenes · 10 test scenes",
      "fields": {
        "Domain": "scenes",
        "Origin": "Synthetic / simulated",
        "Signals": "Geometry / layout, Actions",
        "Other signals": "Goal",
        "Reported scale": "10 test scenes"
      }
    },
    {
      "id": "R35",
      "name": "VBench",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Benchmark",
      "bibkey": "Huang2024VBench",
      "title": "VBench: Comprehensive Benchmark Suite for Video Generative Models",
      "year": 2024,
      "venue": "CVPR",
      "authors": "Huang, Ziqi and He, Yinan and Yu, Jiashuo and Zhang, Fan and Si, Chenyang and Jiang, Yuming and Zhang, Yuanhan and Wu, Tianxing and Jin, Qingyang and Chanpaisit, Nattapol and Wang, Yaohui and Chen, Xinyuan and Wang, Limin and Lin, Dahua and Qiao, Yu and Liu, Ziwei",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Huang_VBench_Comprehensive_Benchmark_Suite_for_Video_Generative_Models_CVPR_2024_paper.html",
      "doi": "10.1109/cvpr52733.2024.02060",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:78",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Huang_VBench_Comprehensive_Benchmark_Suite_for_Video_Generative_Models_CVPR_2024_paper.html",
      "kind": "resource",
      "description": "Benchmark · video · NR",
      "fields": {
        "Domain": "video",
        "Origin": "Synthetic / simulated",
        "Signals": "No selected signal listed",
        "Other signals": "T/Video/Rating",
        "Reported scale": "NR"
      }
    },
    {
      "id": "R36",
      "name": "WorldScore",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Benchmark",
      "bibkey": "Duan2025WorldScore",
      "title": "WorldScore: A Unified Evaluation Benchmark for World Generation",
      "year": 2025,
      "venue": "Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)",
      "authors": "Haoyi Duan and Hong-Xing Yu and Sirui Chen and Fei-Fei, Li and Jiajun Wu",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/ICCV2025/html/Duan_WorldScore_A_Unified_Evaluation_Benchmark_for_World_Generation_ICCV_2025_paper.html",
      "doi": "10.1109/iccv51701.2025.02573",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:79",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/ICCV2025/html/Duan_WorldScore_A_Unified_Evaluation_Benchmark_for_World_Generation_ICCV_2025_paper.html",
      "kind": "resource",
      "description": "Benchmark · video · 3,000 specifications",
      "fields": {
        "Domain": "video",
        "Origin": "NR",
        "Signals": "Pose",
        "Other signals": "T/I/Motion",
        "Reported scale": "3,000 specifications"
      }
    },
    {
      "id": "R37",
      "name": "4DWorldBench",
      "category": "resources",
      "category_label": "Datasets & benchmarks",
      "group": "Benchmark",
      "bibkey": "Lu2026FourDWorldBench",
      "title": "4DWorldBench: A Comprehensive Evaluation Framework for 3D/4D World Generation Models",
      "year": 2026,
      "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
      "authors": "Yiting Lu and Wei Luo and Peiyan Tu and Haoran Li and Hanxin Zhu and Zihao Yu and Xingrui Wang and Xinyi Chen and Xinge Peng and Xin Li and Zhibo Chen",
      "publication_type": "venue_publication",
      "paper_url": "https://openaccess.thecvf.com/content/CVPR2026/html/Lu_4DWorldBench_A_Comprehensive_Evaluation_Framework_for_3D4D_World_Generation_Models_CVPR_2026_paper.html",
      "doi": "",
      "arxiv": "",
      "source": "manuscript/tables/catalogue-resources.tex:81",
      "project_url": "",
      "url": "https://openaccess.thecvf.com/content/CVPR2026/html/Lu_4DWorldBench_A_Comprehensive_Evaluation_Framework_for_3D4D_World_Generation_Models_CVPR_2026_paper.html",
      "kind": "resource",
      "description": "Benchmark · video · NR",
      "fields": {
        "Domain": "video",
        "Origin": "NR",
        "Signals": "No selected signal listed",
        "Other signals": "T/I/Video/Rating",
        "Reported scale": "NR"
      }
    }
  ],
  "field_notes": {
    "NR": "Not established in the inspected material.",
    "—": "Unlisted in the inspected description.",
    "Stage": "P: preparation; A: interactive authoring; R: ongoing generation / prediction.",
    "Evaluation": "U: user study; T: technical test; D: demonstration; X: exploratory study; F: formative study; E: expert assessment; R: ratings; WoZ: Wizard-of-Oz study.",
    "year": "Formal publication year, or initial preprint year for preprint-only records. Preprints and subsequent publications are merged.",
    "descriptions": "Concatenated source-table descriptors, not paper abstracts or capability ratings.",
    "resource_signals": "Selected documented signals; an unlisted signal does not establish absence. Reported scales retain the cited release and unit."
  }
}
