@inproceedings{Poole2023DreamFusion,
  author = {Ben Poole and Ajay Jain and Jonathan T. Barron and Ben Mildenhall},
  title = {{DreamFusion: Text-to-3D using 2D Diffusion}},
  year = {2023},
  booktitle = {The Eleventh International Conference on Learning Representations (ICLR)},
  url = {https://openreview.net/forum?id=FjNys5c7VyY}
}

@inproceedings{Xiang2025TRELLIS,
  doi = {10.1109/cvpr52734.2025.02000},
  author = {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},
  title = {{Structured 3D Latents for Scalable and Versatile 3D Generation}},
  year = {2025},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {21469--21480}
}

@inproceedings{Hollein2023Text2Room,
  doi = {10.1109/iccv51070.2023.00727},
  author = {Lukas H{\"o}llein and Ang Cao and Andrew Owens and Justin Johnson and Matthias Nie{\ss}ner},
  title = {{Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models}},
  year = {2023},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  pages = {7909--7920}
}

@inproceedings{Yang2024Holodeck,
  doi = {10.1109/cvpr52733.2024.01536},
  author = {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},
  title = {{Holodeck: Language Guided Generation of 3D Embodied AI Environments}},
  year = {2024},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {16227--16237}
}

@inproceedings{Bahmani2024FourDfy,
  doi = {10.1109/cvpr52733.2024.00764},
  author = {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},
  title = {{4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling}},
  year = {2024},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {7996--8006}
}

@misc{Ren2023DreamGaussian4D,
  author = {Jiawei Ren and Liang Pan and Jiaxiang Tang and Chi Zhang and Ang Cao and Gang Zeng and Ziwei Liu},
  title = {{DreamGaussian4D: Generative 4D Gaussian Splatting}},
  year = {2023},
  eprint = {2312.17142},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2312.17142},
  url = {https://arxiv.org/abs/2312.17142v3},
  note = {v3, dated 2024-06-10}
}

@inproceedings{Sun2025WorldPlay,
  author = {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},
  title = {{WorldPlay}: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling},
  booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
  series = {Proceedings of Machine Learning Research},
  volume = {306},
  pages = {117501--117523},
  year = {2026},
  publisher = {PMLR},
  url = {https://proceedings.mlr.press/v306/sun26az.html}
}

@inproceedings{Vachha2025Dreamcrafter,
  author = {Cyrus Vachha and Yixiao Kang and Zach Dive and Ashwat Chidambaram and Anik Gupta and Eunice Jun and Bj{\"o}rn Hartmann},
  title = {{Dreamcrafter: Immersive Editing of 3D Radiance Fields Through Flexible, Generative Inputs and Outputs}},
  year = {2025},
  booktitle = {Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems},
  doi = {10.1145/3706598.3714312}
}

@misc{Jiang2026CoGen3D,
  author = {Weiwei Jiang and Wanyu He and Zheyu Tan and Zheyuan Kuang and Difeng Yu and Shinobu Hasegawa and Sven Mayer and Zhanna Sarsenbayeva},
  title = {{CoGen3D: An Agentic Human-AI Co-Design Pipeline for 3D Asset Generation for Virtual Reality}},
  year = {2026},
  eprint = {2607.03731},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2607.03731},
  url = {https://arxiv.org/abs/2607.03731v1},
  note = {v1, dated 2026-07-04}
}

@misc{Zhao2025Hunyuan3D2,
  author = {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},
  title = {{Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation}},
  year = {2025},
  eprint = {2501.12202},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2501.12202},
  url = {https://arxiv.org/abs/2501.12202v1},
  note = {v1, dated 2025-01-21}
}

@inproceedings{Duan2025WorldScore,
  author = {Haoyi Duan and Hong-Xing Yu and Sirui Chen and Fei-Fei, Li and Jiajun Wu},
  title = {{WorldScore: A Unified Evaluation Benchmark for World Generation}},
  year = {2025},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  pages = {27713--27724},
  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}
}

@inproceedings{Lu2026FourDWorldBench,
  author = {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},
  title = {{4DWorldBench: A Comprehensive Evaluation Framework for 3D/4D World Generation Models}},
  year = {2026},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {34322--34332},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Lu_4DWorldBench_A_Comprehensive_Evaluation_Framework_for_3D4D_World_Generation_Models_CVPR_2026_paper.html}
}

@article{ning2026when,
  author = {Xinyu Ning and Yan Zhuo and Xian Wang and Chan-In Devin Sio and Lik-Hang Lee},
  title = {{When Generative Artificial Intelligence Meets Extended Reality: A Systematic Review}},
  year = {2026},
  journal = {International Journal of Human--Computer Interaction},
  volume = {42},
  number = {10},
  pages = {6870--6890},
  doi = {10.1080/10447318.2025.2565392},
  note = {First published online 30 September 2025}
}

@article{rahimi2025generative,
  author = {Fatema Rahimi and Abolghasem Sadeghi-Niaraki and Soo-Mi Choi},
  title = {{Generative AI Meets Virtual Reality: A Comprehensive Survey on Applications, Challenges, and Future Direction}},
  year = {2025},
  journal = {IEEE Access},
  volume = {13},
  pages = {94893--94909},
  doi = {10.1109/ACCESS.2025.3574779}
}

@article{taha2026generative,
  author = {Kamal Taha},
  title = {{Generative AI for multimodal content: a survey with empirical and experimental evaluations}},
  year = {2026},
  journal = {Artificial Intelligence Review},
  volume = {59},
  doi = {10.1007/s10462-026-11525-6},
  note = {Article 140}
}

@article{wang2026visual,
  author = {Duotun Wang and Linjie Qiu and Linlin Cai and Yue Jiang and Mingming Fan and Zeyu Wang},
  title = {{Visual Generative Artificial Intelligence (GenAI) in Mixed Reality (MR): A Survey of Techniques, Interaction Designs, and Evaluations}},
  year = {2026},
  journal = {International Journal of Human--Computer Interaction},
  doi = {10.1080/10447318.2026.2713822},
  note = {Published online 18 August 2026}
}

@inproceedings{hu2025generative,
  author = {Kaiyuan Hu and Yili Jin and Hao Zhou and Linfeng Du and Jiangchuan Liu and Xue Liu},
  title = {{Generative AI for Immersive Video: Recent Advances and Future Opportunities}},
  year = {2025},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence},
  pages = {10464--10472},
  doi = {10.24963/ijcai.2025/1162},
  url = {https://www.ijcai.org/proceedings/2025/1162}
}

@misc{kong2025world,
  author = {Lingdong Kong and Yu Yang and Jianbiao Mei and Youquan Liu and Ao Liang and Dekai Zhu and Dongyue Lu and Wei Yin and Xiaotao Hu and Mingkai Jia and Junyuan Deng and Kaiwen Zhang and Yang Wu and Tianyi Yan and Shenyuan Gao and Song Wang and Linfeng Li and Liang Pan and Yong Liu and Jianke Zhu and Wei Tsang Ooi and Steven C. H. Hoi and Ziwei Liu},
  title = {{3D and 4D World Modeling: A Survey}},
  year = {2025},
  eprint = {2509.07996},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2509.07996},
  url = {https://arxiv.org/abs/2509.07996v4},
  note = {Version 4, revised 20 July 2026}
}

@inproceedings{Lin2023Magic3D,
  doi = {10.1109/cvpr52729.2023.00037},
  author = {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},
  title = {{Magic3D: High-Resolution Text-to-3D Content Creation}},
  year = {2023},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {300--309},
  month = {June}
}

@inproceedings{Xiang2026TRELLIS2,
  author = {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},
  title = {{Native and Compact Structured Latents for 3D Generation}},
  year = {2026},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {14419--14429},
  month = {June},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Xiang_Native_and_Compact_Structured_Latents_for_3D_Generation_CVPR_2026_paper.html}
}

@inproceedings{Lin2025PartCrafter,
  author = {Yuchen Lin and Chenguo Lin and Panwang Pan and Honglei Yan and Yiqiang Feng and Yadong Mu and Katerina Fragkiadaki},
  title = {{PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers}},
  year = {2025},
  booktitle = {Advances in Neural Information Processing Systems},
  volume = {38},
  pages = {35387--35415},
  publisher = {Curran Associates, Inc.},
  doi = {10.52202/085713-1189},
  url = {https://proceedings.neurips.cc/paper_files/paper/2025/hash/32cc61322f1e2f56f989d29ccc7cfbb7-Abstract-Conference.html}
}

@inproceedings{Fridman2023SceneScape,
  author = {Rafail Fridman and Amit Abecasis and Yoni Kasten and Tali Dekel},
  title = {{SceneScape: Text-Driven Consistent Scene Generation}},
  year = {2023},
  booktitle = {Advances in Neural Information Processing Systems},
  volume = {36},
  pages = {39897--39914},
  publisher = {Curran Associates, Inc.},
  doi = {10.52202/075280-1734},
  url = {https://papers.neurips.cc/paper_files/paper/2023/hash/7d62a85ebfed2f680eb5544beae93191-Abstract-Conference.html}
}

@article{Chen2023SceneDreamer,
  author = {Zhaoxi Chen and Guangcong Wang and Ziwei Liu},
  title = {{SceneDreamer: Unbounded 3D Scene Generation From 2D Image Collections}},
  year = {2023},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume = {45},
  number = {12},
  pages = {15562--15576},
  month = {December},
  doi = {10.1109/TPAMI.2023.3321857}
}

@misc{HunyuanWorldTeam2025HunyuanWorld,
  author = {{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},
  title = {{HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels}},
  year = {2025},
  eprint = {2507.21809},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2507.21809},
  url = {https://arxiv.org/abs/2507.21809v1},
  note = {Technical report, v1, dated 2025-07-29}
}

@misc{HYWorldTeam2026HYWorld2,
  author = {{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},
  title = {{HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds}},
  year = {2026},
  eprint = {2604.14268},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2604.14268},
  url = {https://arxiv.org/abs/2604.14268v1},
  note = {Technical report, v1, dated 2026-04-15}
}

@article{Huang2025Voyager,
  author = {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},
  title = {{Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation}},
  year = {2025},
  journal = {ACM Transactions on Graphics},
  volume = {44},
  number = {6},
  pages = {1--15},
  articleno = {245},
  numpages = {15},
  month = {December},
  doi = {10.1145/3763330},
  note = {Article 245}
}

@inproceedings{Tang2023MVDiffusion,
  author = {Tang, Shitao and Zhang, Fuyang and Chen, Jiacheng and Wang, Peng and Furukawa, Yasutaka},
  title = {{MVDiffusion}: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2023},
  volume = {36},
  pages = {51202--51233},
  publisher = {Curran Associates, Inc.},
  doi = {10.52202/075280-2229},
  url = {https://proceedings.nips.cc/paper_files/paper/2023/hash/a0da690a47b2f52faa63f6fe054057b5-Abstract-Conference.html}
}

@misc{Mandal2026EPIC,
  author = {Mandal, Debabrata and Fu, Dongdong and Miller, Jonathon and Villareal, William and Peng, Xi and Chakravarthula, Praneeth},
  title = {{EPIC}: Epipolar-Consistent 360-Degree Immersive Stereo Video Generation},
  year = {2026},
  eprint = {2609.38689},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  doi = {10.48550/arXiv.2609.38689},
  url = {https://arxiv.org/abs/2609.38689v1},
  note = {Preprint, v1, dated 2026-09-30}
}

@inproceedings{Sun2025DimensionX,
  author = {Wenqiang Sun and Shuo Chen and Fangfu Liu and Zilong Chen and Yueqi Duan and Jun Zhu and Jun Zhang and Yikai Wang},
  title = {{DimensionX: Create Any 3D and 4D Scenes from a Single Image with Decoupled Video Diffusion}},
  year = {2025},
  month = oct,
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  pages = {13695--13706},
  url = {https://openaccess.thecvf.com/content/ICCV2025/html/Sun_DimensionX_Create_Any_3D_and_4D_Scenes_from_a_Single_ICCV_2025_paper.html},
  note = {Technical analysis uses arXiv:2411.04928v1 (2024), titled ``DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion''},
  doi = {10.1109/iccv51701.2025.01271}
}

@misc{He2025MatrixGame2,
  author = {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},
  title = {{Matrix-game 2.0: An open-source real-time and streaming interactive world model}},
  year = {2025},
  eprint = {2508.13009},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2508.13009},
  url = {https://arxiv.org/abs/2508.13009v2},
  note = {Version 2, revised 24 November 2025}
}

@misc{Wang2026MatrixGame3,
  author = {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},
  title = {{Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory}},
  year = {2026},
  eprint = {2604.08995},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2604.08995},
  url = {https://arxiv.org/abs/2604.08995v1},
  note = {Version 1, posted 10 April 2026}
}

@misc{ParkerHolder2025Genie3,
  author = {Jack Parker-Holder and Shlomi Fruchter},
  title = {{Genie 3: A new frontier for world models}},
  year = {2025},
  month = aug,
  howpublished = {Google DeepMind research blog},
  url = {https://deepmind.google/blog/genie-3-a-new-frontier-for-world-models/},
  note = {Published 5 August 2025; accessed 21 October 2026}
}

@inproceedings{Zhang2024VRCopilot,
  author = {Lei Zhang and Jin Pan and Jacob Gettig and Steve Oney and Anhong Guo},
  title = {{VRCopilot: Authoring 3D Layouts with Generative AI Models in VR}},
  booktitle = {Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology},
  year = {2024},
  pages = {1--13},
  publisher = {Association for Computing Machinery},
  doi = {10.1145/3654777.3676451}
}

@inproceedings{Tong2025MS2MeshXR,
  author = {Yuqi Tong and Yue Qiu and Ruiyang Li and Shi Qiu and Pheng-Ann Heng},
  title = {{MS2Mesh-XR: Multi-Modal Sketch-to-Mesh Generation in XR Environments}},
  booktitle = {2025 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)},
  year = {2025},
  pages = {272--276},
  publisher = {IEEE},
  doi = {10.1109/AIxVR63409.2025.00052}
}

@inproceedings{Paschalidou2021ATISS,
  author = {Despoina Paschalidou and Amlan Kar and Maria Shugrina and Karsten Kreis and Andreas Geiger and Sanja Fidler},
  title = {{ATISS: Autoregressive Transformers for Indoor Scene Synthesis}},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2021},
  volume = {34},
  pages = {12013--12026},
  publisher = {Curran Associates, Inc.},
  url = {https://proceedings.neurips.cc/paper/2021/hash/64986d86a17424eeac96b08a6d519059-Abstract.html}
}

@inproceedings{Zhang2023ControlNet,
  doi = {10.1109/iccv51070.2023.00355},
  author = {Lvmin Zhang and Anyi Rao and Maneesh Agrawala},
  title = {{Adding Conditional Control to Text-to-Image Diffusion Models}},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  year = {2023},
  pages = {3836--3847}
}

@inproceedings{Wang2024CRM,
  author = {Zhengyi Wang and Yikai Wang and Yifei Chen and Chendong Xiang and Shuo Chen and Dajiang Yu and Chongxuan Li and Hang Su and Jun Zhu},
  title = {{CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model}},
  booktitle = {Computer Vision -- ECCV 2024},
  year = {2024},
  pages = {57--74},
  publisher = {Springer Nature Switzerland},
  doi = {10.1007/978-3-031-72751-1_4}
}

@inproceedings{Tamir2025Stereoscopic,
  author = {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},
  title = {{What Makes for a Good Stereoscopic Image?}},
  year = {2025},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  pages = {261--272},
  month = {June},
  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}
}

@inproceedings{Xie2026GeneratedReality,
  author = {Xie, Linxi and Sun, Lisong C. and Neall, Ashley and Wu, Tong and Cai, Shengqu and Wetzstein, Gordon},
  title = {{Generated Reality}: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control},
  booktitle = {CVPR 2026 Findings},
  year = {2026},
  url = {https://arxiv.org/abs/2602.18422v1},
  eprint = {2602.18422},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  note = {Findings venue identified by the official author project. Technical version inspected: arXiv:2602.18422v1, 20 February 2026},
  doi = {10.1109/cvprf71909.2026.00387}
}

@article{Nguyen2026ImmersiveHAI,
  author = {Nguyen, Thu and Simoff, Simeon J. and Qu, Zhonglin and Adam, Rani and Catchpoole, Daniel R. and Kennedy, Paul J. and Nguyen, Quang Vinh},
  title = {Generative Artificial Intelligence and Human Artificial Intelligence Interaction in Immersive Environments: Research and Development Directions},
  journal = {International Journal of Human--Computer Interaction},
  year = {2026},
  doi = {10.1080/10447318.2026.2719170},
  note = {Published online 26 August 2026}
}

@misc{Ye2026Embodied3DSurvey,
  author = {Ye, Tianwei and Mao, Yifan and Liao, Minwen and Liu, Jian and Guo, Chunchao and Du, Dazhao and Shou, Quanxin and Zhu, Fangqi and Guo, Song},
  title = {{3D} Generation for Embodied {AI} and Robotic Simulation: A Survey},
  year = {2026},
  eprint = {2604.26509},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  doi = {10.48550/arXiv.2604.26509},
  url = {https://arxiv.org/abs/2604.26509v3},
  note = {Version 3, 8 May 2026}
}

@inproceedings{Lee2026HOICraft,
  author = {Lee, Dohui and Sun, Qi and Yoon, Sang Ho},
  title = {{HOICraft}: In-Situ {VLM}-based Authoring Tool for Part-Level Hand-Object Interaction Design in {VR}},
  booktitle = {Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems},
  year = {2026},
  pages = {1--25},
  publisher = {Association for Computing Machinery},
  doi = {10.1145/3772318.3790823},
}

@misc{Po2026MultiGen,
  author = {Po, Ryan and Zhang, David Junhao and Hertz, Amir and Wetzstein, Gordon and Wadhwa, Neal and Ruiz, Nataniel},
  title = {{MultiGen}: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines},
  year = {2026},
  eprint = {2603.06679},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  doi = {10.48550/arXiv.2603.06679},
  url = {https://arxiv.org/abs/2603.06679v2},
  note = {Version 2, 30 March 2026}
}

@inproceedings{Lee2025ImaginateAR,
  author = {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},
  title = {{ImaginateAR}: {AI}-Assisted In-Situ Authoring in Augmented Reality},
  booktitle = {Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology},
  series = {UIST '25},
  year = {2025},
  articleno = {52},
  publisher = {Association for Computing Machinery},
  doi = {10.1145/3746059.3747635},
}

@article{Liu2026HeritagePrototyping,
  author = {Liu, Jianquan and Li, Runnan and Zhao, Haiying},
  title = {Generative {AI}-Assisted Visualization Prototyping for Cultural Heritage: A Computational Framework from {2D} Planes to {3D} Immersive Scenes},
  journal = {Buildings},
  year = {2026},
  volume = {16},
  number = {16},
  pages = {3319},
  doi = {10.3390/buildings16163319},
}

@article{Han2026PanoramicStimuli,
  author = {Han, Yoojin and Jeong, Joowon},
  title = {Leveraging Generative {AI} for High-Fidelity 360{\textdegree} Spatial Images: Methodological Validation for Use as Experimental Stimuli},
  journal = {Buildings},
  year = {2026},
  volume = {16},
  number = {9},
  pages = {1679},
  doi = {10.3390/buildings16091679},
}

@article{Xie2026SceneSurvey,
  author = {Xie, Haozhe and Wen, Beichen and Chen, Zhaoxi and Hong, Fangzhou and Liu, Ziwei},
  title = {{3D} Scene Generation: A Survey},
  journal = {International Journal of Computer Vision},
  year = {2026},
  volume = {134},
  doi = {10.1007/s11263-026-02999-6},
  url = {https://link.springer.com/article/10.1007/s11263-026-02999-6},
  note = {Article 418}
}

@inproceedings{Mildenhall2020NeRF,
  author = {Ben Mildenhall and Pratul P. Srinivasan and Matthew Tancik and Jonathan T. Barron and Ravi Ramamoorthi and Ren Ng},
  title = {{NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis}},
  year = {2020},
  booktitle = {ECCV 2020},
  url = {https://arxiv.org/abs/2003.08934},
  doi = {10.1007/978-3-030-58452-8_24}
}

@article{Kerbl2023GaussianSplatting,
  author = {Bernhard Kerbl and Georgios Kopanas and Thomas Leimk{\"{u}}hler and George Drettakis},
  title = {{3D Gaussian Splatting for Real-Time Radiance Field Rendering}},
  year = {2023},
  journal = {ACM Transactions on Graphics},
  volume = {42},
  number = {4},
  url = {https://arxiv.org/abs/2308.04079},
  doi = {10.1145/3592433}
}

@inproceedings{Radford2021CLIP,
  author = {Alec Radford and Jong Wook Kim and Chris Hallacy and Aditya Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever},
  title = {{Learning Transferable Visual Models From Natural Language Supervision}},
  year = {2021},
  booktitle = {Proceedings of the 38th International Conference on Machine Learning},
  url = {https://proceedings.mlr.press/v139/radford21a.html},
  series = {PMLR},
  volume = {139},
  pages = {8748--8763}
}

@inproceedings{Wang2023ProlificDreamer,
  author = {Zhengyi Wang and Cheng Lu and Yikai Wang and Fan Bao and Chongxuan Li and Hang Su and Jun Zhu},
  title = {{ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation}},
  year = {2023},
  booktitle = {NeurIPS 2023},
  url = {https://arxiv.org/abs/2305.16213}
}

@misc{Jun2023ShapE,
  author = {Heewoo Jun and Alex Nichol},
  title = {{Shap-E: Generating Conditional 3D Implicit Functions}},
  year = {2023},
  note = {arXiv preprint},
  eprint = {2305.02463},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.02463}
}

@inproceedings{Liu2023Zero123,
  author = {Ruoshi Liu and Rundi Wu and Van Hoorick, Basile and Pavel Tokmakov and Sergey Zakharov and Carl Vondrick},
  title = {{Zero-1-to-3: Zero-shot One Image to 3D Object}},
  year = {2023},
  booktitle = {ICCV 2023},
  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}
}

@inproceedings{Hong2024LRM,
  author = {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},
  title = {{LRM: Large Reconstruction Model for Single Image to 3D}},
  year = {2024},
  booktitle = {ICLR 2024},
  url = {https://arxiv.org/abs/2311.04400}
}

@misc{Xu2024InstantMesh,
  author = {Jiale Xu and Weihao Cheng and Yiming Gao and Xintao Wang and Shenghua Gao and Ying Shan},
  title = {{InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models}},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2404.07191},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.07191}
}

@inproceedings{Shi2024MVDream,
  author = {Yichun Shi and Peng Wang and Jianglong Ye and Long Mai and Kejie Li and Xiao Yang},
  title = {{MVDream: Multi-view Diffusion for 3D Generation}},
  year = {2024},
  booktitle = {ICLR 2024},
  url = {https://proceedings.iclr.cc/paper_files/paper/2024/hash/adbe936993aa7cf41e45054d8b72f183-Abstract-Conference.html}
}

@misc{Li2025TripoSG,
  author = {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},
  title = {{TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models}},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2502.06608},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.06608}
}

@misc{Yang2025HoloPart,
  author = {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},
  title = {{HoloPart: Generative 3D Part Amodal Segmentation}},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2504.07943},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.07943}
}

@inproceedings{Tang2024LGM,
  author = {Jiaxiang Tang and Zhaoxi Chen and Xiaokang Chen and Tengfei Wang and Gang Zeng and Ziwei Liu},
  title = {{LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation}},
  year = {2024},
  booktitle = {ECCV 2024},
  url = {https://arxiv.org/abs/2402.05054},
  doi = {10.1007/978-3-031-73235-5_1}
}

@inproceedings{Deitke2023Objaverse,
  author = {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},
  title = {{Objaverse: A Universe of Annotated 3D Objects}},
  year = {2023},
  booktitle = {CVPR 2023},
  url = {https://arxiv.org/abs/2212.08051},
  doi = {10.1109/cvpr52729.2023.01263}
}

@inproceedings{Collins2022ABO,
  author = {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},
  title = {{ABO: Dataset and Benchmarks for Real-World 3D Object Understanding}},
  year = {2022},
  booktitle = {CVPR 2022},
  url = {https://arxiv.org/abs/2110.06199},
  doi = {10.1109/cvpr52688.2022.02045}
}

@misc{Chang2015ShapeNet,
  author = {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},
  title = {{ShapeNet: An Information-Rich 3D Model Repository}},
  year = {2015},
  note = {arXiv preprint},
  eprint = {1512.03012},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1512.03012}
}

@inproceedings{Chen2025ThreeDTopiaXL,
  author = {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},
  title = {{3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion}},
  year = {2025},
  booktitle = {CVPR 2025},
  url = {https://arxiv.org/abs/2409.12957},
  doi = {10.1109/cvpr52734.2025.02475}
}

@inproceedings{Lan2024LN3Diff,
  author = {Yushi Lan and Fangzhou Hong and Shuai Yang and Shangchen Zhou and Xuyi Meng and Bo Dai and Xingang Pan and Chen Change Loy},
  title = {{LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation}},
  year = {2024},
  booktitle = {ECCV 2024},
  url = {https://arxiv.org/abs/2403.12019v2},
  doi = {10.1007/978-3-031-73235-5_7}
}

@inproceedings{Pumarola2021DNeRF,
  author = {Albert Pumarola and Enric Corona and Gerard Pons-Moll and Francesc Moreno-Noguer},
  title = {{D-NeRF: Neural Radiance Fields for Dynamic Scenes}},
  year = {2021},
  booktitle = {CVPR 2021},
  url = {https://openaccess.thecvf.com/content/CVPR2021/html/Pumarola_D-NeRF_Neural_Radiance_Fields_for_Dynamic_Scenes_CVPR_2021_paper.html},
  doi = {10.1109/cvpr46437.2021.01018}
}

@inproceedings{FridovichKeil2023KPlanes,
  author = {Sara Fridovich-Keil and Giacomo Meanti and Frederik Rahb{\ae}k Warburg and Benjamin Recht and Angjoo Kanazawa},
  title = {{K-Planes: Explicit Radiance Fields in Space, Time, and Appearance}},
  year = {2023},
  booktitle = {CVPR 2023},
  url = {https://openaccess.thecvf.com/content/CVPR2023/html/Fridovich-Keil_K-Planes_Explicit_Radiance_Fields_in_Space_Time_and_Appearance_CVPR_2023_paper.html},
  doi = {10.1109/cvpr52729.2023.01201}
}

@misc{Ye2023IPAdapter,
  author = {Hu Ye and Jun Zhang and Sibo Liu and Xiao Han and Wei Yang},
  title = {{IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models}},
  year = {2023},
  note = {arXiv preprint},
  eprint = {2308.06721},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2308.06721}
}

@article{Oquab2024DINOv2,
  author = {Maxime Oquab and Timoth{\'{e}}e Darcet and Th{\'{e}}o Moutakanni and Huy V. Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Herv{\'{e}} Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
  title = {{DINOv2: Learning Robust Visual Features without Supervision}},
  year = {2024},
  journal = {Transactions on Machine Learning Research},
  url = {https://arxiv.org/abs/2304.07193}
}

@inproceedings{Szegedy2016InceptionV3,
  author = {Christian Szegedy and Vincent Vanhoucke and Sergey Ioffe and Jon Shlens and Zbigniew Wojna},
  title = {{Rethinking the Inception Architecture for Computer Vision}},
  year = {2016},
  booktitle = {CVPR 2016},
  url = {https://openaccess.thecvf.com/content_cvpr_2016/html/Szegedy_Rethinking_the_Inception_CVPR_2016_paper.html},
  doi = {10.1109/cvpr.2016.308}
}

@article{Wang2004SSIM,
  author = {Zhou Wang and Alan C. Bovik and Hamid R. Sheikh and Eero P. Simoncelli},
  title = {{Image Quality Assessment: From Error Visibility to Structural Similarity}},
  year = {2004},
  journal = {IEEE Transactions on Image Processing},
  volume = {13},
  number = {4},
  pages = {600--612},
  doi = {10.1109/TIP.2003.819861},
  url = {https://www.ece.uwaterloo.ca/~z70wang/publications/ssim.html}
}

@inproceedings{Rombach2022LDM,
  author = {Robin Rombach and Andreas Blattmann and Dominik Lorenz and Patrick Esser and Bj{\"{o}}rn Ommer},
  title = {{High-Resolution Image Synthesis with Latent Diffusion Models}},
  year = {2022},
  booktitle = {CVPR 2022},
  url = {https://arxiv.org/abs/2112.10752},
  doi = {10.1109/cvpr52688.2022.01042}
}

@inproceedings{Tang2024DreamGaussian,
  author = {Jiaxiang Tang and Jiawei Ren and Hang Zhou and Ziwei Liu and Gang Zeng},
  title = {{DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation}},
  year = {2024},
  booktitle = {ICLR 2024},
  url = {https://proceedings.iclr.cc/paper_files/paper/2024/hash/905202e21386913d8eac637c2b50f590-Abstract-Conference.html}
}

@inproceedings{Liu2024SyncDreamer,
  author = {Yuan Liu and Cheng Lin and Zijiao Zeng and Xiaoxiao Long and Lingjie Liu and Taku Komura and Wenping Wang},
  title = {{SyncDreamer: Generating Multiview-consistent Images from a Single-view Image}},
  year = {2024},
  booktitle = {ICLR 2024},
  url = {https://arxiv.org/abs/2309.03453}
}

@inproceedings{Richardson2023TEXTure,
  author = {Elad Richardson and Gal Metzer and Yuval Alaluf and Raja Giryes and Daniel Cohen-Or},
  title = {{TEXTure: Text-Guided Texturing of 3D Shapes}},
  year = {2023},
  booktitle = {SIGGRAPH 2023 Conference Papers},
  url = {https://arxiv.org/abs/2302.01721},
  doi = {10.1145/3588432.3591503}
}

@inproceedings{Chen2023Fantasia3D,
  author = {Rui Chen and Yongwei Chen and Ningxin Jiao and Kui Jia},
  title = {{Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation}},
  year = {2023},
  booktitle = {ICCV 2023},
  url = {https://arxiv.org/abs/2303.13873},
  doi = {10.1109/iccv51070.2023.02033}
}

@inproceedings{Deitke2023ObjaverseXL,
  author = {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},
  title = {{Objaverse-XL: A Universe of 10M+ 3D Objects}},
  year = {2023},
  booktitle = {NeurIPS 2023 Datasets and Benchmarks Track},
  doi = {10.52202/075280-1554},
  url = {https://proceedings.neurips.cc/paper_files/paper/2023/hash/70364304877b5e767de4e9a2a511be0c-Abstract-Datasets_and_Benchmarks.html}
}

@inproceedings{Xu2024GRM,
  author = {Yinghao Xu and Zifan Shi and Wang, Yifan and Hansheng Chen and Ceyuan Yang and Sida Peng and Yujun Shen and Gordon Wetzstein},
  title = {{GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation}},
  year = {2024},
  booktitle = {ECCV 2024},
  url = {https://arxiv.org/abs/2403.14621},
  doi = {10.1007/978-3-031-72633-0_1}
}

@inproceedings{Haque2023InstructNeRF2NeRF,
  author = {Ayaan Haque and Matthew Tancik and Alexei A. Efros and Aleksander Holynski and Angjoo Kanazawa},
  title = {{Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions}},
  year = {2023},
  booktitle = {ICCV 2023},
  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}
}

@inproceedings{Zhou2025SEVA,
  author = {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},
  title = {{Stable Virtual Camera: Generative View Synthesis with Diffusion Models}},
  year = {2025},
  booktitle = {ICCV 2025},
  pages = {12405--12414},
  doi = {10.1109/ICCV51701.2025.01153},
  url = {https://openaccess.thecvf.com/content/ICCV2025/html/Zhou_Stable_Virtual_Camera_Generative_View_Synthesis_with_Diffusion_Models_ICCV_2025_paper.html}
}

@article{Yu2025ViewCrafter,
  author = {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},
  title = {{ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis}},
  year = {2025},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  doi = {10.1109/TPAMI.2025.3613256},
  url = {https://drexubery.github.io/ViewCrafter/}
}

@inproceedings{Ren2025GEN3C,
  author = {Xuanchi Ren and Tianchang Shen and Jiahui Huang and Huan Ling and Yifan Lu and Merlin Nimier-David and Thomas M{\"{u}}ller and Alexander Keller and Sanja Fidler and Jun Gao},
  title = {{GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control}},
  year = {2025},
  booktitle = {CVPR 2025},
  pages = {6121--6132},
  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}
}

@inproceedings{Engstler2025InvisibleStitch,
  author = {Paul Engstler and Andrea Vedaldi and Iro Laina and Christian Rupprecht},
  title = {{Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting}},
  year = {2025},
  booktitle = {International Conference on 3D Vision (3DV) 2025},
  pages = {457--468},
  doi = {10.1109/3DV66043.2025.00047},
  url = {https://robots.ox.ac.uk/~vgg/publications/2025/Engstler25/}
}

@inproceedings{Tang2024DiffuScene,
  author = {Jiapeng Tang and Yinyu Nie and Lev Markhasin and Angela Dai and Justus Thies and Matthias Nie{\ss}ner},
  title = {{DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis}},
  year = {2024},
  booktitle = {CVPR 2024},
  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}
}

@inproceedings{Lin2024InstructScene,
  author = {Chenguo Lin and Yadong Mu},
  title = {{InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior}},
  year = {2024},
  booktitle = {ICLR 2024},
  url = {https://chenguolin.github.io/projects/InstructScene/}
}

@inproceedings{Yang2024PhyScene,
  author = {Yandan Yang and Baoxiong Jia and Peiyuan Zhi and Siyuan Huang},
  title = {{PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI}},
  year = {2024},
  booktitle = {CVPR 2024},
  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}
}

@article{Chung2025LucidDreamerScenes,
  author = {Jaeyoung Chung and Suyoung Lee and Hyeongjin Nam and Jaerin Lee and Kyoung Mu Lee},
  title = {{LucidDreamer: Domain-Free Generation of 3D Gaussian Splatting Scenes}},
  year = {2025},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  volume = {31},
  number = {12},
  doi = {10.1109/TVCG.2025.3611489},
  url = {https://luciddreamer-cvlab.github.io/}
}

@inproceedings{Yu2024WonderJourney,
  author = {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},
  title = {{WonderJourney: Going from Anywhere to Everywhere}},
  year = {2024},
  booktitle = {CVPR 2024},
  pages = {6658--6667},
  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}
}

@inproceedings{Yu2025WonderWorld,
  author = {Hong-Xing Yu and Haoyi Duan and Charles Herrmann and William T. Freeman and Jiajun Wu},
  title = {{WonderWorld: Interactive 3D Scene Generation from a Single Image}},
  year = {2025},
  booktitle = {CVPR 2025},
  url = {https://kovenyu.com/wonderworld/},
  doi = {10.1109/cvpr52734.2025.00555}
}

@inproceedings{Zhang2024PanFusion,
  author = {Cheng Zhang and Qianyi Wu and Camilo Cruz Gambardella and Xiaoshui Huang and Dinh Phung and Wanli Ouyang and Jianfei Cai},
  title = {{Taming Stable Diffusion for Text to 360{\ensuremath{^\circ}} Panorama Image Generation}},
  year = {2024},
  booktitle = {CVPR 2024},
  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}
}

@inproceedings{Xing2026StereoWorldConversion,
  author = {Ke Xing and Longfei Li and Yuyang Yin and Hanwen Liang and Guixun Luo and Chen Fang and Jue Wang and Konstantinos N. Plataniotis and Xiaojie Jin and Yao Zhao and Yunchao Wei},
  title = {{StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation}},
  year = {2026},
  booktitle = {CVPR 2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Xing_StereoWorld_Geometry-Aware_Monocular-to-Stereo_Video_Generation_CVPR_2026_paper.html}
}

@inproceedings{Sun2026StereoWorldModel,
  author = {Yang-Tian Sun and Zehuan Huang and Yifan Niu and Lin Ma and Yan-Pei Cao and Yuewen Ma and Xiaojuan Qi},
  title = {{Stereo World Model: Camera-Guided Stereo Video Generation}},
  year = {2026},
  booktitle = {CVPR 2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Sun_Stereo_World_Model_Camera-Guided_Stereo_Video_Generation_CVPR_2026_paper.html}
}

@inproceedings{Chen2024GaussianEditor,
  author = {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},
  title = {{GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting}},
  year = {2024},
  booktitle = {CVPR 2024},
  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}
}

@inproceedings{Bokhovkin2025SceneFactor,
  author = {Aleksey Bokhovkin and Quan Meng and Shubham Tulsiani and Angela Dai},
  title = {{SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation}},
  year = {2025},
  booktitle = {CVPR 2025},
  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}
}

@inproceedings{Fu2021ThreeDFRONT,
  author = {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},
  title = {{3D-FRONT: 3D Furnished Rooms With layOuts and semaNTics}},
  year = {2021},
  booktitle = {ICCV 2021},
  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}
}

@inproceedings{Ling2024DL3DV,
  author = {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},
  title = {{DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision}},
  year = {2024},
  booktitle = {CVPR 2024},
  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}
}

@article{Zhou2018StereoMagnification,
  author = {Tinghui Zhou and Richard Tucker and John Flynn and Graham Fyffe and Noah Snavely},
  title = {{Stereo Magnification: Learning View Synthesis Using Multiplane Images}},
  year = {2018},
  journal = {ACM Transactions on Graphics},
  volume = {37},
  url = {https://research.google/pubs/stereo-magnification-learning-view-synthesis-using-multiplane-images/},
  doi = {10.1145/3197517.3201323}
}

@inproceedings{Ma2025See3D,
  author = {Baorui Ma and Huachen Gao and Haoge Deng and Zhengxiong Luo and Tiejun Huang and Lulu Tang and Xinlong Wang},
  title = {{You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale}},
  year = {2025},
  booktitle = {CVPR 2025},
  url = {https://arxiv.org/abs/2412.06699},
  doi = {10.1109/cvpr52734.2025.00194}
}

@inproceedings{Chen2025FlexWorld,
  author = {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},
  title = {{FlexWorld: Progressively Expanding 3D Scenes for Flexible-View Exploration}},
  year = {2025},
  booktitle = {NeurIPS 2025},
  doi = {10.52202/085713-5732},
  url = {https://papers.neurips.cc/paper_files/paper/2025/hash/fb23e1cbc747c96c07c7a1681b567c35-Abstract-Conference.html}
}

@inproceedings{Feng2023LayoutGPT,
  author = {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},
  title = {{LayoutGPT: Compositional Visual Planning and Generation with Large Language Models}},
  year = {2023},
  booktitle = {NeurIPS 2023},
  doi = {10.52202/075280-0802},
  url = {https://proceedings.neurips.cc/paper_files/paper/2023/hash/3a7f9e485845dac27423375c934cb4db-Abstract.html}
}

@inproceedings{Yang2024SceneCraft,
  author = {Xiuyu Yang and Yunze Man and Jun-Kun Chen and Yu-Xiong Wang},
  title = {{SceneCraft: Layout-Guided 3D Scene Generation}},
  year = {2024},
  booktitle = {NeurIPS 2024},
  url = {https://orangesodahub.github.io/SceneCraft/}
}

@inproceedings{Zhou2024DreamScene360,
  author = {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},
  title = {{DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting}},
  year = {2024},
  booktitle = {ECCV 2024},
  url = {https://dreamscene360.github.io/},
  doi = {10.1007/978-3-031-72658-3_19}
}

@inproceedings{Wang2024ThreeSixtyDVD,
  author = {Qian Wang and Weiqi Li and Chong Mou and Xinhua Cheng and Jian Zhang},
  title = {{360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model}},
  year = {2024},
  booktitle = {CVPR 2024},
  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}
}

@inproceedings{Li2026CubeComposer,
  author = {Lingen Li and Guangzhi Wang and Xiaoyu Li and Zhaoyang Zhang and Qi Dou and Jinwei Gu and Tianfan Xue and Ying Shan},
  title = {{CubeComposer: Spatio-Temporal Autoregressive 4K 360{\ensuremath{^\circ}} Video Generation from Perspective Video}},
  year = {2026},
  booktitle = {CVPR 2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Li_CubeComposer_Spatio-Temporal_Autoregressive_4K_360deg_Video_Generation_from_Perspective_Video_CVPR_2026_paper.html}
}

@inproceedings{Wang2024StereoDiffusion,
  author = {Lezhong Wang and Jeppe Revall Frisvad and Mark Bo Jensen and Siavash Arjomand Bigdeli},
  title = {{StereoDiffusion: Training-Free Stereo Image Generation Using Latent Diffusion Models}},
  year = {2024},
  booktitle = {CVPR Workshops 2024 (GCV)},
  doi = {10.1109/CVPRW63382.2024.00737},
  url = {https://arxiv.org/abs/2403.04965}
}

@misc{Zhao2024StereoCrafter,
  author = {Sijie Zhao and Wenbo Hu and Xiaodong Cun and Yong Zhang and Xiaoyu Li and Zhe Kong and Xiangjun Gao and Muyao Niu and Ying Shan},
  title = {{StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos}},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2409.07447},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.07447}
}

@inproceedings{Qiu2026Pano3DComposer,
  author = {Zidian Qiu and Ancong Wu},
  title = {{Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image}},
  year = {2026},
  booktitle = {CVPR 2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Qiu_Pano3DComposer_Feed-Forward_Compositional_3D_Scene_Generation_from_Single_Panoramic_Image_CVPR_2026_paper.html}
}

@inproceedings{Singer2023MAV3D,
  author = {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},
  title = {{Text-To-4D Dynamic Scene Generation}},
  year = {2023},
  booktitle = {ICML},
  url = {https://proceedings.mlr.press/v202/singer23a.html}
}

@inproceedings{Jiang2024Consistent4D,
  author = {Jiang, Yanqin and Zhang, Li and Gao, Jin and Hu, Weiming and Yao, Yao},
  title = {{Consistent4D: Consistent 360{\ensuremath{^\circ}} Dynamic Object Generation from Monocular Video}},
  year = {2024},
  booktitle = {ICLR},
  url = {https://proceedings.iclr.cc/paper_files/paper/2024/hash/e33a77969c26e5efdf3989ac46e7a036-Abstract-Conference.html}
}

@inproceedings{Xie2025SV4D,
  author = {Xie, Yiming and Yao, Chun-Han and Voleti, Vikram and Jiang, Huaizu and Jampani, Varun},
  title = {{SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency}},
  year = {2025},
  booktitle = {ICLR},
  url = {https://proceedings.iclr.cc/paper_files/paper/2025/hash/5297e56ac65ba2bfa70ee9fc4818c042-Abstract-Conference.html}
}

@inproceedings{Wu2025CAT4D,
  author = {Wu, Rundi and Gao, Ruiqi and Poole, Ben and Trevithick, Alex and Zheng, Changxi and Barron, Jonathan T. and Holynski, Aleksander},
  title = {{CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models}},
  year = {2025},
  booktitle = {CVPR},
  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}
}

@inproceedings{Bruce2024Genie,
  author = {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 Rockt{\"{a}}schel},
  title = {{Genie: Generative Interactive Environments}},
  year = {2024},
  booktitle = {ICML},
  url = {https://proceedings.mlr.press/v235/bruce24a.html}
}

@inproceedings{Valevski2025GameNGen,
  author = {Valevski, Dani and Leviathan, Yaniv and Arar, Moab and Fruchter, Shlomi},
  title = {{Diffusion Models Are Real-Time Game Engines}},
  year = {2025},
  booktitle = {ICLR},
  url = {https://proceedings.iclr.cc/paper_files/paper/2025/hash/b71ecea210f7159f31e46631fe5c838f-Abstract-Conference.html}
}

@inproceedings{Xiao2025WorldMem,
  author = {Xiao, Zeqi and Lan, Yushi and Zhou, Yifan and Ouyang, Wenqi and Yang, Shuai and Zeng, Yanhong and Pan, Xingang},
  title = {{WorldMem: Long-term Consistent World Simulation with Memory}},
  year = {2025},
  booktitle = {NeurIPS},
  url = {https://arxiv.org/html/2504.12369v2}
}

@inproceedings{Li2025VMem,
  author = {Runjia Li and Philip Torr and Andrea Vedaldi and Tomas Jakab},
  title = {{VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory}},
  year = {2025},
  booktitle = {ICCV},
  url = {https://v-mem.github.io/},
  doi = {10.1109/iccv51701.2025.02383}
}

@inproceedings{Garcin2026PERSIST,
  author = {Samuel Garcin and Thomas Walker and Steven Mcdonagh and Tim Pearce and Hakan Bilen and Tianyu He and Kaixin Wang and Jiang Bian},
  title = {{Beyond Pixel Histories: World Models with Persistent 3D State}},
  year = {2026},
  booktitle = {ICML},
  url = {https://proceedings.mlr.press/v306/garcin26a.html}
}

@misc{Li2025GameCraft,
  author = {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},
  title = {{Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition}},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2506.17201},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.17201}
}

@inproceedings{He2025CameraCtrl,
  author = {He, Hao and Xu, Yinghao and Guo, Yuwei and Wetzstein, Gordon and DAI, Bo and Li, Hongsheng and Yang, Ceyuan},
  title = {{CameraCtrl: Enabling Camera Control for Video Diffusion Models}},
  year = {2025},
  booktitle = {ICLR},
  url = {https://proceedings.iclr.cc/paper_files/paper/2025/hash/f98fd73d59d8494489ea970747b91fe4-Abstract-Conference.html}
}

@misc{Unterthiner2018FVD,
  author = {Unterthiner, Thomas and van Steenkiste, Sjoerd and Kurach, Karol and Marinier, Raphael and Michalski, Marcin and Gelly, Sylvain},
  title = {{Towards Accurate Generative Models of Video: A New Metric \& Challenges}},
  year = {2018},
  note = {arXiv preprint},
  eprint = {1812.01717},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1812.01717}
}

@inproceedings{Zhang2018LPIPS,
  author = {Zhang, Richard and Isola, Phillip and Efros, Alexei A. and Shechtman, Eli and Wang, Oliver},
  title = {{The Unreasonable Effectiveness of Deep Features as a Perceptual Metric}},
  year = {2018},
  booktitle = {CVPR},
  doi = {10.1109/CVPR.2018.00068},
  url = {https://arxiv.org/abs/1801.03924}
}

@misc{Li2026PixelsStates,
  author = {Li, Zhen and Meng, Zian and Shi, Shuwei and Zhai, Mingliang and Tan, Jiaming and Li, Chuanhao and Zhang, Kaipeng},
  title = {{From Pixels to States: Rethinking Interactive World Models as Game Engines}},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2607.14076},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.14076}
}

@inproceedings{Xing2024DynamiCrafter,
  author = {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},
  title = {{DynamiCrafter: Animating Open-Domain Images with Video Diffusion Priors}},
  year = {2024},
  booktitle = {Computer Vision - ECCV 2024},
  doi = {10.1007/978-3-031-72952-2_23},
  url = {https://link.springer.com/chapter/10.1007/978-3-031-72952-2_23}
}

@misc{Xu2024EasyAnimate,
  author = {Jiaqi Xu and Xinyi Zou and Kunzhe Huang and Yunkuo Chen and Bo Liu and MengLi Cheng and Xing Shi and Jun Huang},
  title = {{EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture}},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2405.18991},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2405.18991},
  url = {https://arxiv.org/abs/2405.18991v1}
}

@misc{Zhou2024Allegro,
  author = {Yuan Zhou and Qiuyue Wang and Yuxuan Cai and Huan Yang},
  title = {{Allegro: Open the Black Box of Commercial-Level Video Generation Model}},
  year = {2024},
  note = {arXiv preprint},
  eprint = {2410.15458},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2410.15458},
  url = {https://arxiv.org/abs/2410.15458}
}

@inproceedings{Yang2025CogVideoX,
  author = {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},
  title = {{CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer}},
  year = {2025},
  booktitle = {ICLR 2025},
  url = {https://proceedings.iclr.cc/paper_files/paper/2025/file/ce31378e9f41d8907e97dab172b6c559-Paper-Conference.pdf}
}

@inproceedings{Ling2024AlignGaussians,
  author = {Ling, Huan and Kim, Seung Wook and Torralba, Antonio and Fidler, Sanja and Kreis, Karsten},
  title = {{Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models}},
  year = {2024},
  booktitle = {CVPR},
  url = {https://arxiv.org/abs/2312.13763},
  doi = {10.1109/cvpr52733.2024.00819}
}

@inproceedings{Alonso2024DIAMOND,
  author = {Eloi Alonso and Adam Jelley and Vincent Micheli and Anssi Kanervisto and Amos Storkey and Tim Pearce and Francois Fleuret},
  title = {{Diffusion for World Modeling: Visual Details Matter in Atari}},
  year = {2024},
  booktitle = {NeurIPS},
  url = {https://papers.neurips.cc/paper_files/paper/2024/file/6bdde0373d53d4a501249547084bed43-Paper-Conference.pdf}
}

@inproceedings{Wu2025SpatialMemory,
  author = {Wu, Tong and Yang, Shuai and Po, Ryan and Xu, Yinghao and Liu, Ziwei and Lin, Dahua and Wetzstein, Gordon},
  title = {{Video World Models with Long-term Spatial Memory}},
  year = {2025},
  booktitle = {NeurIPS},
  url = {https://arxiv.org/abs/2506.05284}
}

@inproceedings{Po2025SSMWorld,
  author = {Po, Ryan and Nitzan, Yotam and Zhang, Richard and Chen, Berlin and Dao, Tri and Shechtman, Eli and Wetzstein, Gordon and Huang, Xun},
  title = {{Long-Context State-Space Video World Models}},
  year = {2025},
  booktitle = {ICCV},
  url = {https://arxiv.org/abs/2505.20171},
  doi = {10.1109/iccv51701.2025.00817}
}

@misc{Chen2026ReWorld,
  author = {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},
  title = {{ReWorld: An Interactive World Model with Long-Horizon Memory}},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2608.23565},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.23565}
}

@misc{Tang2025GameCraft2,
  author = {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},
  title = {{Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model}},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2511.23429},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.23429}
}

@inproceedings{Wang2024MotionCtrl,
  author = {Wang, Zhouxia and Yuan, Ziyang and Wang, Xintao and Li, Yaowei and Chen, Tianshui and Xia, Menghan and Luo, Ping and Shan, Ying},
  title = {{MotionCtrl: A Unified and Flexible Motion Controller for Video Generation}},
  year = {2024},
  booktitle = {SIGGRAPH Conference Papers},
  doi = {10.1145/3641519.3657518},
  url = {https://arxiv.org/abs/2312.03641}
}

@inproceedings{Huang2024VBench,
  author = {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},
  title = {{VBench: Comprehensive Benchmark Suite for Video Generative Models}},
  year = {2024},
  booktitle = {CVPR},
  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}
}

@inproceedings{Heusel2017FID,
  author = {Heusel, Martin and Ramsauer, Hubert and Unterthiner, Thomas and Nessler, Bernhard and Hochreiter, Sepp},
  title = {{GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium}},
  year = {2017},
  booktitle = {NeurIPS},
  url = {https://papers.nips.cc/paper_files/paper/2017/hash/8a1d694707eb0fefe65871369074926d-Abstract.html}
}

@inproceedings{Shen2025GaussianShopVR,
  author = {Yulin Shen and Boyu Li and Jiayang Huang and David Yip and Zeyu Wang},
  title = {{GaussianShopVR: Facilitating Immersive 3D Authoring Using Gaussian Splatting in VR}},
  year = {2025},
  booktitle = {UIST 2025},
  doi = {10.1145/3746059.3747803},
  url = {https://cislab.hkust-gz.edu.cn/projects/gaussianshopvr/}
}

@inproceedings{Wang2026Roomify,
  author = {Xueyang Wang and Qinxuan Cen and Weitao Bi and Yunxiang Ma and Xin Yi and Robert Xiao and Xinyi Fu and Hewu Li},
  title = {{Roomify: Spatially-Grounded Style Transformation for Immersive Virtual Environments}},
  year = {2026},
  booktitle = {CHI 2026},
  doi = {10.1145/3772318.3791803},
  url = {https://arxiv.org/abs/2603.04917}
}

@inproceedings{Weng2026EditingReality,
  author = {Suibi Che-Chuan Weng and Shih-Yu Ma and Sawyer Reinig and Pritalee Kadam and Ada Yi Zhao and Amy Bani{\'{c}} and Ryo Suzuki and Ellen Yi-Luen Do},
  title = {{Editing Reality: Designing In-Situ Co-Creation with Generative AI in Mixed Reality}},
  year = {2026},
  booktitle = {DIS 2026},
  doi = {10.1145/3800645.3813087},
  url = {https://www.colorado.edu/atlas/editing-reality-situ-co-creation-generative-ai-mixed-reality}
}

@inproceedings{Zhang2025FusionProtor,
  author = {Hongbo Zhang and Pei Chen and Xuelong Xie and Zhaoqu Jiang and Yifei Wu and Zejian Li and Xiaoyu Chen and Lingyun Sun},
  title = {{FusionProtor: A Mixed-Prototype Tool for Component-level Physical-to-Virtual 3D Transition and Simulation}},
  year = {2025},
  booktitle = {CHI 2025},
  doi = {10.1145/3706598.3713686},
  url = {https://hongboooo.github.io/files/fusion.pdf}
}

@inproceedings{Hu2025Thing2Reality,
  author = {Erzhen Hu and Mingyi Li and Jungtaek Hong and Xun Qian and Alex Olwal and David Kim and Seongkook Heo and Ruofei Du},
  title = {{Thing2Reality: Enabling Spontaneous Creation of 3D Objects from 2D Content using Generative AI in XR Meetings}},
  year = {2025},
  booktitle = {UIST 2025},
  doi = {10.1145/3746059.3747621},
  url = {https://erzhenh.com/pdfs/uist25_Thing2Reality.pdf}
}

@inproceedings{Numan2024SpaceBlender,
  author = {Nels Numan and Shwetha Rajaram and Balasaravanan Thoravi Kumaravel and Nicolai Marquardt and Andrew D. Wilson},
  title = {{SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending}},
  year = {2024},
  booktitle = {UIST 2024},
  doi = {10.1145/3654777.3676361},
  url = {https://arxiv.org/abs/2409.13926}
}

@inproceedings{Xiu2025SayItSeeIt,
  author = {Yanming Xiu and Joshua Chilukuri and Shunav Sen and Maria Gorlatova},
  title = {{Say It, See It: A Systematic Evaluation on Speech-Based 3D Content Generation Methods in Augmented Reality}},
  year = {2025},
  booktitle = {IEEE ISMAR Adjunct 2025; UNAI workshop},
  doi = {10.1109/ISMAR-Adjunct68609.2025.00069},
  url = {https://scholars.duke.edu/publication/1705223}
}

@inproceedings{Yang2024DreamSpace,
  author = {Bangbang Yang and Wenqi Dong and Lin Ma and Wenbo Hu and Xiao Liu and Zhaopeng Cui and Yuewen Ma},
  title = {{DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagation}},
  year = {2024},
  booktitle = {IEEE VR 2024},
  doi = {10.1109/VR58804.2024.00085},
  url = {https://ybbbbt.com/publication/dreamspace/}
}

@inproceedings{Hu2024GenerativeTerrain,
  author = {Yushen Hu and Keru Wang and Yuli Shao and Jan Plass and Zhu Wang and Ken Perlin},
  title = {{Generative Terrain Authoring with Mid-air Hand Sketching in Virtual Reality}},
  year = {2024},
  booktitle = {ACM VRST 2024},
  doi = {10.1145/3641825.3687736},
  url = {https://cs.unm.edu/~zhuwang/assets/pdf/VR_Terrain_Generation_VRST_2024.pdf}
}

@inproceedings{Li2025VideoCraft,
  author = {Boyu Li and Lin-Ping Yuan and Zeyu Wang},
  title = {{VideoCraft: A Mixed Reality-empowered Video Generation Workflow with Spatial Layer Editing for Concept Video Creation}},
  year = {2025},
  booktitle = {UIST 2025},
  doi = {10.1145/3746059.3747606},
  url = {https://cislab.hkust-gz.edu.cn/publications/videocraft-a-mixed-reality-empowered-video-generation-workflow-with-spatial-layer-editing-for-concept-video-creation/}
}

@inproceedings{Weng2024DreamMesh,
  author = {Suibi Che-Chuan Weng and Yan-Ming Chiou and Ellen Yi-Luen Do},
  title = {{Dream Mesh: A Speech-to-3D Model Generative Pipeline in Mixed Reality}},
  year = {2024},
  booktitle = {IEEE AIxVR 2024},
  doi = {10.1109/AIxVR59861.2024.00059},
  url = {https://www.researchgate.net/publication/378580267_Dream_Mesh_A_Speech-to-3D_Model_Generative_Pipeline_in_Mixed_Reality}
}

@inproceedings{Behravan2025ContextAware3D,
  author = {Majid Behravan and Kre{\v{s}}imir Matkovi{\'{c}} and Denis Gra{\v{c}}anin},
  title = {{Generative AI for Context-Aware 3D Object Creation Using Vision-Language Models in Augmented Reality}},
  year = {2025},
  booktitle = {IEEE AIxVR 2025},
  doi = {10.1109/AIxVR63409.2025.00018},
  url = {https://www.vrvis.at/en/publications/PB-VRVis-2025-022}
}

@inproceedings{Yao2025Gesture2Prop,
  author = {Zhihao Yao and Xiwen Yao and Qirui Sun and Haowei Xiong and Kin Wang Lau and Haipeng Mi},
  title = {{Gesture2Prop: Conditional VR Prop Generation from Hand Gestures and Speech}},
  year = {2025},
  booktitle = {UIST Adjunct 2025},
  doi = {10.1145/3746058.3759017},
  url = {https://haowei-xiong-sowilo-research-station.webflow.io/post/posts/gesture2prop-conditional-vr-prop-generation-from-handgestures-and-speech}
}

@inproceedings{Rasch2025CreepyCoCreator,
  author = {Julian Rasch and Julia T{\"{o}}ws and Teresa Hirzle and Florian M{\"{u}}ller and Martin Schmitz},
  title = {{CreepyCoCreator? Investigating AI Representation Modes for 3D Object Co-Creation in Virtual Reality}},
  year = {2025},
  booktitle = {CHI 2025},
  doi = {10.1145/3706598.3713720},
  url = {https://arxiv.org/abs/2502.03069}
}

@inproceedings{DeLaTorre2024LLMR,
  author = {De La Torre, Fernanda and Cathy Mengying Fang and Han Huang and Andrzej Banburski-Fahey and Judith Amores Fernandez and Jaron Lanier},
  title = {{LLMR: Real-time Prompting of Interactive Worlds using Large Language Models}},
  year = {2024},
  booktitle = {CHI 2024},
  doi = {10.1145/3613904.3642579},
  url = {https://arxiv.org/abs/2309.12276}
}

@inproceedings{Limbert2025ImoGenXR,
  author = {George Limbert and Abhijit Karnik},
  title = {{ImoGenXR: Investigating the Impact on Creativity Support in a Generative-AI Assisted Immersive Authoring Workflow}},
  year = {2025},
  booktitle = {11th International Conference on Virtual Reality (ICVR 2025)},
  doi = {10.1109/ICVR66534.2025.11172549},
  url = {https://eprints.lancs.ac.uk/229355/1/VR1013.pdf}
}

@misc{Li2025EmbodiedSurvey,
  author = {Xinqing Li and Xin He and Le Zhang and Min Wu and Xiaoli Li and Yun Liu},
  title = {{A Comprehensive Survey on World Models for Embodied AI}},
  year = {2025},
  eprint = {2510.16732},
  archivePrefix = {arXiv},
  note = {Version 3, revised June 2026},
  url = {https://arxiv.org/abs/2510.16732v3}
}

@misc{Shang2025EmbodiedSurvey,
  author = {Yu Shang and Yinzhou Tang and Xin Zhang and Shengyuan Wang and Yuwei Yan and Honglin Zhang and Zhiheng Zheng and Jie Zhao and Jie Feng and Chen Gao and Jiansheng Chen and Yong Li},
  title = {{A Survey of Embodied World Models}},
  year = {2025},
  note = {Author-hosted preprint; supplied twelve-author edition},
  url = {https://fi.ee.tsinghua.edu.cn/public/publications/0940dda4-af15-11f0-9d60-0242ac120002.pdf}
}

@article{Azuma1997AR,
  title = {{A Survey of Augmented Reality}},
  author = {Azuma, Ronald T.},
  year = {1997},
  journal = {Presence: Teleoperators and Virtual Environments},
  volume = {6},
  pages = {355--385},
  doi = {10.1162/pres.1997.6.4.355},
  url = {https://doi.org/10.1162/pres.1997.6.4.355},
  number = {4}
}

@article{Azuma2001AR,
  title = {{Recent advances in augmented reality}},
  author = {Azuma, Ronald and Baillot, Yohan and Behringer, Reinhold and Feiner, Steven and Julier, Simon and MacIntyre, Blair},
  year = {2001},
  journal = {IEEE Computer Graphics and Applications},
  volume = {21},
  pages = {34--47},
  doi = {10.1109/38.963459},
  url = {https://doi.org/10.1109/38.963459},
  number = {6}
}

@inproceedings{Speicher2019MR,
  title = {{What is Mixed Reality?}},
  author = {Speicher, Maximilian and Hall, Brian D. and Nebeling, Michael},
  year = {2019},
  booktitle = {Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems},
  pages = {1--15},
  doi = {10.1145/3290605.3300767},
  url = {https://doi.org/10.1145/3290605.3300767}
}

@article{Slater1997Framework,
  title = {{A Framework for Immersive Virtual Environments (FIVE): Speculations on the Role of Presence in Virtual Environments}},
  author = {Slater, Mel and Wilbur, Sylvia},
  year = {1997},
  journal = {Presence: Teleoperators and Virtual Environments},
  volume = {6},
  pages = {603--616},
  doi = {10.1162/pres.1997.6.6.603},
  url = {https://doi.org/10.1162/pres.1997.6.6.603},
  number = {6}
}

@article{Slater2009Illusions,
  title = {{Place illusion and plausibility can lead to realistic behaviour in immersive virtual environments}},
  author = {Slater, Mel},
  year = {2009},
  journal = {Philosophical Transactions of the Royal Society B: Biological Sciences},
  volume = {364},
  pages = {3549--3557},
  doi = {10.1098/rstb.2009.0138},
  url = {https://doi.org/10.1098/rstb.2009.0138},
  number = {1535}
}

@article{SanchezVives2005Presence,
  title = {{From presence to consciousness through virtual reality}},
  author = {Sanchez-Vives, Maria V. and Slater, Mel},
  year = {2005},
  journal = {Nature Reviews Neuroscience},
  volume = {6},
  pages = {332--339},
  doi = {10.1038/nrn1651},
  url = {https://doi.org/10.1038/nrn1651},
  number = {4}
}

@article{Witmer1998Presence,
  title = {{Measuring Presence in Virtual Environments: A Presence Questionnaire}},
  author = {Witmer, Bob G. and Singer, Michael J.},
  year = {1998},
  journal = {Presence: Teleoperators and Virtual Environments},
  volume = {7},
  pages = {225--240},
  doi = {10.1162/105474698565686},
  url = {https://doi.org/10.1162/105474698565686},
  number = {3}
}

@article{Schubert2001Presence,
  title = {{The Experience of Presence: Factor Analytic Insights}},
  author = {Schubert, Thomas and Friedmann, Frank and Regenbrecht, Holger},
  year = {2001},
  journal = {Presence: Teleoperators and Virtual Environments},
  volume = {10},
  pages = {266--281},
  doi = {10.1162/105474601300343603},
  url = {https://doi.org/10.1162/105474601300343603},
  number = {3}
}

@article{Usoh2000Presence,
  title = {{Using Presence Questionnaires in Reality}},
  author = {Usoh, Martin and Catena, Ernest and Arman, Sima and Slater, Mel},
  year = {2000},
  journal = {Presence: Teleoperators and Virtual Environments},
  volume = {9},
  pages = {497--503},
  doi = {10.1162/105474600566989},
  url = {https://doi.org/10.1162/105474600566989},
  number = {5}
}

@article{Kilteni2012Embodiment,
  title = {{The Sense of Embodiment in Virtual Reality}},
  author = {Kilteni, Konstantina and Groten, Raphaela and Slater, Mel},
  year = {2012},
  journal = {Presence: Teleoperators and Virtual Environments},
  volume = {21},
  pages = {373--387},
  doi = {10.1162/pres_a_00124},
  url = {https://doi.org/10.1162/pres_a_00124},
  number = {4}
}

@article{Slater2010Body,
  title = {{First Person Experience of Body Transfer in Virtual Reality}},
  author = {Slater, Mel and Spanlang, Bernhard and Sanchez-Vives, Maria V. and Blanke, Olaf},
  year = {2010},
  journal = {PLoS ONE},
  volume = {5},
  pages = {e10564},
  doi = {10.1371/journal.pone.0010564},
  url = {https://doi.org/10.1371/journal.pone.0010564},
  number = {5}
}

@article{Hoffman2008VAC,
  title = {{Vergence–accommodation conflicts hinder visual performance and cause visual fatigue}},
  author = {Hoffman, David M. and Girshick, Ahna R. and Akeley, Kurt and Banks, Martin S.},
  year = {2008},
  journal = {Journal of Vision},
  volume = {8},
  pages = {33},
  doi = {10.1167/8.3.33},
  url = {https://doi.org/10.1167/8.3.33},
  number = {3}
}

@article{Shibata2011Comfort,
  title = {{The zone of comfort: Predicting visual discomfort with stereo displays}},
  author = {Shibata, Takashi and Kim, Joohwan and Hoffman, David M. and Banks, Martin S.},
  year = {2011},
  journal = {Journal of Vision},
  volume = {11},
  pages = {11--11},
  doi = {10.1167/11.8.11},
  url = {https://doi.org/10.1167/11.8.11},
  number = {8}
}

@article{Banks2012Stereo,
  title = {{Stereoscopy and the Human Visual System}},
  author = {Banks, Martin S. and Read, Jenny C. A. and Allison, Robert S. and Watt, Simon J.},
  year = {2012},
  journal = {SMPTE Motion Imaging Journal},
  volume = {121},
  pages = {24--43},
  doi = {10.5594/j18173},
  url = {https://doi.org/10.5594/j18173},
  number = {4}
}

@article{Kramida2016VAC,
  title = {{Resolving the Vergence-Accommodation Conflict in Head-Mounted Displays}},
  author = {Kramida, Gregory},
  year = {2016},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  volume = {22},
  pages = {1912--1931},
  doi = {10.1109/tvcg.2015.2473855},
  url = {https://doi.org/10.1109/tvcg.2015.2473855},
  number = {7}
}

@article{Padmanaban2017Focus,
  title = {{Optimizing virtual reality for all users through gaze-contingent and adaptive focus displays}},
  author = {Padmanaban, Nitish and Konrad, Robert and Stramer, Tal and Cooper, Emily A. and Wetzstein, Gordon},
  year = {2017},
  journal = {Proceedings of the National Academy of Sciences},
  volume = {114},
  pages = {2183--2188},
  doi = {10.1073/pnas.1617251114},
  url = {https://doi.org/10.1073/pnas.1617251114},
  number = {9}
}

@article{Akeley2004Focus,
  title = {{A stereo display prototype with multiple focal distances}},
  author = {Akeley, Kurt and Watt, Simon J. and Girshick, Ahna Reza and Banks, Martin S.},
  year = {2004},
  journal = {ACM Transactions on Graphics},
  volume = {23},
  pages = {804--813},
  doi = {10.1145/1015706.1015804},
  url = {https://doi.org/10.1145/1015706.1015804},
  number = {3}
}

@inproceedings{Sutherland1968HMD,
  title = {{A head-mounted three dimensional display}},
  author = {Sutherland, Ivan E.},
  year = {1968},
  booktitle = {Proceedings of the December 9-11, 1968, fall joint computer conference, part I on - AFIPS '68 (Fall, part I)},
  pages = {757--764},
  doi = {10.1145/1476589.1476686},
  url = {https://doi.org/10.1145/1476589.1476686}
}

@article{Welch2002Tracking,
  title = {{Motion tracking: no silver bullet, but a respectable arsenal}},
  author = {Welch, Greg and Foxlin, Eric},
  year = {2002},
  journal = {IEEE Computer Graphics and Applications},
  volume = {22},
  pages = {24--38},
  doi = {10.1109/mcg.2002.1046626},
  url = {https://doi.org/10.1109/mcg.2002.1046626},
  number = {6}
}

@article{Holloway1997Registration,
  title = {{Registration Error Analysis for Augmented Reality}},
  author = {Holloway, Richard L.},
  year = {1997},
  journal = {Presence: Teleoperators and Virtual Environments},
  volume = {6},
  pages = {413--432},
  doi = {10.1162/pres.1997.6.4.413},
  url = {https://doi.org/10.1162/pres.1997.6.4.413},
  number = {4}
}

@inproceedings{Azuma1994Registration,
  title = {{Improving static and dynamic registration in an optical see-through HMD}},
  author = {Azuma, Ronald and Bishop, Gary},
  year = {1994},
  booktitle = {Proceedings of the 21st annual conference on Computer graphics and interactive techniques  - SIGGRAPH '94},
  pages = {197--204},
  doi = {10.1145/192161.192199},
  url = {https://doi.org/10.1145/192161.192199}
}

@inproceedings{Jerald2009Latency,
  title = {{Relating Scene-Motion Thresholds to Latency Thresholds for Head-Mounted Displays}},
  author = {Jerald, Jason and Whitton, Mary C.},
  year = {2009},
  booktitle = {2009 IEEE Virtual Reality Conference},
  pages = {211--218},
  doi = {10.1109/vr.2009.4811025},
  url = {https://doi.org/10.1109/vr.2009.4811025}
}

@inproceedings{Mania2004Latency,
  title = {{Perceptual sensitivity to head tracking latency in virtual environments with varying degrees of scene complexity}},
  author = {Mania, Katerina and Adelstein, Bernard D. and Ellis, Stephen R. and Hill, Michael I.},
  year = {2004},
  booktitle = {Proceedings of the 1st Symposium on Applied perception in graphics and visualization},
  pages = {39--47},
  doi = {10.1145/1012551.1012559},
  url = {https://doi.org/10.1145/1012551.1012559}
}

@article{Warburton2023Latency,
  title = {{Measuring motion-to-photon latency for sensorimotor experiments with virtual reality systems}},
  author = {Warburton, Matthew and Mon-Williams, Mark and Mushtaq, Faisal and Morehead, J. Ryan},
  year = {2023},
  journal = {Behavior Research Methods},
  volume = {55},
  pages = {3658--3678},
  doi = {10.3758/s13428-022-01983-5},
  url = {https://doi.org/10.3758/s13428-022-01983-5},
  number = {7}
}

@inproceedings{VanWaveren2016Timewarp,
  title = {{The asynchronous time warp for virtual reality on consumer hardware}},
  author = {van Waveren, J. M. P.},
  year = {2016},
  booktitle = {Proceedings of the 22nd ACM Conference on Virtual Reality Software and Technology},
  pages = {37--46},
  doi = {10.1145/2993369.2993375},
  url = {https://doi.org/10.1145/2993369.2993375}
}

@article{Friston2014Latency,
  title = {{Measuring Latency in Virtual Environments}},
  author = {Friston, Sebastian and Steed, Anthony},
  year = {2014},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  volume = {20},
  pages = {616--625},
  doi = {10.1109/tvcg.2014.30},
  url = {https://doi.org/10.1109/tvcg.2014.30},
  number = {4}
}

@inproceedings{Poupyrev1996GoGo,
  title = {{The go-go interaction technique}},
  author = {Poupyrev, Ivan and Billinghurst, Mark and Weghorst, Suzanne and Ichikawa, Tadao},
  year = {1996},
  booktitle = {Proceedings of the 9th annual ACM symposium on User interface software and technology  - UIST '96},
  pages = {79--80},
  doi = {10.1145/237091.237102},
  url = {https://doi.org/10.1145/237091.237102}
}

@inproceedings{Bowman1997Manipulation,
  title = {{An evaluation of techniques for grabbing and manipulating remote objects in immersive virtual environments}},
  author = {Bowman, Doug A. and Hodges, Larry F.},
  year = {1997},
  booktitle = {Proceedings of the 1997 symposium on Interactive 3D graphics  - SI3D '97},
  pages = {35--ff.},
  doi = {10.1145/253284.253301},
  url = {https://doi.org/10.1145/253284.253301}
}

@inproceedings{Mine1997Proprioception,
  title = {{Moving Objects in Space: Exploiting Proprioception in Virtual-Environment Interaction}},
  author = {Mine, Mark R. and Brooks, Jr., Frederick P. and Séquin, Carlo H.},
  year = {1997},
  booktitle = {Proceedings of the 24th annual conference on Computer graphics and interactive techniques  - SIGGRAPH '97},
  pages = {19--26},
  doi = {10.1145/258734.258747},
  url = {https://doi.org/10.1145/258734.258747}
}

@article{Steinicke2010Walking,
  title = {{Estimation of Detection Thresholds for Redirected Walking Techniques}},
  author = {Steinicke, Frank and Bruder, Gerd and Jerald, Jason and Frenz, Harald and Lappe, Markus},
  year = {2010},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  volume = {16},
  pages = {17--27},
  doi = {10.1109/tvcg.2009.62},
  url = {https://doi.org/10.1109/tvcg.2009.62},
  number = {1}
}

@article{Billinghurst2001MagicBook,
  title = {{The MagicBook: a transitional AR interface}},
  author = {Billinghurst, Mark and Kato, Hirokazu and Poupyrev, Ivan},
  year = {2001},
  journal = {Computers \& Graphics},
  volume = {25},
  pages = {745--753},
  doi = {10.1016/s0097-8493(01)00117-0},
  url = {https://doi.org/10.1016/s0097-8493(01)00117-0},
  number = {5}
}

@article{Ens2019Collaboration,
  title = {{Revisiting collaboration through mixed reality: The evolution of groupware}},
  author = {Ens, Barrett and Lanir, Joel and Tang, Anthony and Bateman, Scott and Lee, Gun and Piumsomboon, Thammathip and Billinghurst, Mark},
  year = {2019},
  journal = {International Journal of Human-Computer Studies},
  volume = {131},
  pages = {81--98},
  doi = {10.1016/j.ijhcs.2019.05.011},
  url = {https://doi.org/10.1016/j.ijhcs.2019.05.011}
}

@article{Kennedy1993SSQ,
  title = {{Simulator Sickness Questionnaire: An Enhanced Method for Quantifying Simulator Sickness}},
  author = {Kennedy, Robert S. and Lane, Norman E. and Berbaum, Kevin S. and Lilienthal, Michael G.},
  year = {1993},
  journal = {The International Journal of Aviation Psychology},
  volume = {3},
  pages = {203--220},
  doi = {10.1207/s15327108ijap0303_3},
  url = {https://doi.org/10.1207/s15327108ijap0303_3},
  number = {3}
}

@article{Saredakis2020Sickness,
  title = {{Factors Associated With Virtual Reality Sickness in Head-Mounted Displays: A Systematic Review and Meta-Analysis}},
  author = {Saredakis, Dimitrios and Szpak, Ancret and Birckhead, Brandon and Keage, Hannah A. D. and Rizzo, Albert and Loetscher, Tobias},
  year = {2020},
  journal = {Frontiers in Human Neuroscience},
  volume = {14},
  doi = {10.3389/fnhum.2020.00096},
  url = {https://doi.org/10.3389/fnhum.2020.00096}
}

@article{Weech2019Sickness,
  title = {{Presence and Cybersickness in Virtual Reality Are Negatively Related: A Review}},
  author = {Weech, Séamas and Kenny, Sophie and Barnett-Cowan, Michael},
  year = {2019},
  journal = {Frontiers in Psychology},
  volume = {10},
  doi = {10.3389/fpsyg.2019.00158},
  url = {https://doi.org/10.3389/fpsyg.2019.00158}
}

@incollection{Hart1988TLX,
  title = {{Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research}},
  author = {Hart, Sandra G. and Staveland, Lowell E.},
  year = {1988},
  booktitle = {Human Mental Workload},
  volume = {52},
  pages = {139--183},
  doi = {10.1016/s0166-4115(08)62386-9},
  url = {https://doi.org/10.1016/s0166-4115(08)62386-9},
  series = {Advances in Psychology},
  publisher = {North-Holland},
  editor = {Hancock, Peter A. and Meshkati, Najmedin}
}

@article{Lewis1995Usability,
  title = {{IBM computer usability satisfaction questionnaires: Psychometric evaluation and instructions for use}},
  author = {Lewis, James R.},
  year = {1995},
  journal = {International Journal of Human-Computer Interaction},
  volume = {7},
  pages = {57--78},
  doi = {10.1080/10447319509526110},
  url = {https://doi.org/10.1080/10447319509526110},
  number = {1}
}

@article{Cummings2016Immersion,
  title = {{How Immersive Is Enough? A Meta-Analysis of the Effect of Immersive Technology on User Presence}},
  author = {Cummings, James J. and Bailenson, Jeremy N.},
  year = {2016},
  journal = {Media Psychology},
  volume = {19},
  pages = {272--309},
  doi = {10.1080/15213269.2015.1015740},
  url = {https://doi.org/10.1080/15213269.2015.1015740},
  number = {2}
}

@article{McMahan2012Fidelity,
  title = {{Evaluating Display Fidelity and Interaction Fidelity in a Virtual Reality Game}},
  author = {McMahan, Ryan P. and Bowman, Doug A. and Zielinski, David J. and Brady, Rachael B.},
  year = {2012},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  volume = {18},
  pages = {626--633},
  doi = {10.1109/tvcg.2012.43},
  url = {https://doi.org/10.1109/tvcg.2012.43},
  number = {4}
}

@inproceedings{Schwind2019Presence,
  title = {{Using Presence Questionnaires in Virtual Reality}},
  author = {Schwind, Valentin and Knierim, Pascal and Haas, Nico and Henze, Niels},
  year = {2019},
  booktitle = {Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems},
  pages = {1--12},
  doi = {10.1145/3290605.3300590},
  url = {https://doi.org/10.1145/3290605.3300590}
}

@inproceedings{Klein2007PTAM,
  title = {{Parallel Tracking and Mapping for Small AR Workspaces}},
  author = {Klein, Georg and Murray, David},
  year = {2007},
  booktitle = {2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality},
  pages = {1--10},
  doi = {10.1109/ismar.2007.4538852},
  url = {https://doi.org/10.1109/ismar.2007.4538852}
}

@article{Campos2021ORBSLAM3,
  title = {{ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM}},
  author = {Campos, Carlos and Elvira, Richard and Rodriguez, Juan J. Gomez and M. Montiel, Jose M. and D. Tardos, Juan},
  year = {2021},
  journal = {IEEE Transactions on Robotics},
  volume = {37},
  pages = {1874--1890},
  doi = {10.1109/tro.2021.3075644},
  url = {https://doi.org/10.1109/tro.2021.3075644},
  number = {6}
}

@inproceedings{Piumsomboon2018MiniMe,
  title = {{Mini-Me: An Adaptive Avatar for Mixed Reality Remote Collaboration}},
  author = {Piumsomboon, Thammathip and Lee, Gun A. and Hart, Jonathon D. and Ens, Barrett and Lindeman, Robert W. and Thomas, Bruce H. and Billinghurst, Mark},
  year = {2018},
  booktitle = {Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems},
  pages = {1--13},
  doi = {10.1145/3173574.3173620},
  url = {https://doi.org/10.1145/3173574.3173620}
}

@inproceedings{Dai2017ScanNet,
  title = {{ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes}},
  author = {Dai, Angela and Chang, Angel X. and Savva, Manolis and Halber, Maciej and Funkhouser, Thomas and Niessner, Matthias},
  year = {2017},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages = {5828--5839},
  url = {https://openaccess.thecvf.com/content_cvpr_2017/html/Dai_ScanNet_Richly-Annotated_3D_CVPR_2017_paper.html},
  doi = {10.1109/cvpr.2017.261}
}

@inproceedings{Chang2017Matterport3D,
  title = {{Matterport3D: Learning from RGB-D Data in Indoor Environments}},
  author = {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},
  year = {2017},
  booktitle = {2017 International Conference on 3D Vision (3DV)},
  doi = {10.1109/3dv.2017.00081},
  url = {https://arxiv.org/abs/1709.06158}
}

@misc{Straub2019Replica,
  title = {{The Replica Dataset: A Digital Replica of Indoor Spaces}},
  author = {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},
  year = {2019},
  eprint = {1906.05797},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1906.05797}
}

@inproceedings{Yeshwanth2023ScanNetPP,
  title = {{ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes}},
  author = {Yeshwanth, Chandan and Liu, Yueh-Cheng and Nießner, Matthias and Dai, Angela},
  year = {2023},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages = {12--22},
  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}
}

@inproceedings{Baruch2021ARKitScenes,
  title = {{ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data}},
  author = {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},
  year = {2021},
  booktitle = {Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks},
  volume = {1},
  url = {https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/66f041e16a60928b05a7e228a89c3799-Abstract-round1.html}
}

@inproceedings{Ramakrishnan2021HM3D,
  title = {{Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI}},
  author = {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},
  year = {2021},
  booktitle = {Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks},
  volume = {1},
  url = {https://datasets-benchmarks-proceedings.neurips.cc/paper_files/paper/2021/hash/34173cb38f07f89ddbebc2ac9128303f-Abstract-round2.html}
}

@inproceedings{Savva2019Habitat,
  title = {{Habitat: A Platform for Embodied AI Research}},
  author = {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},
  year = {2019},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages = {9339--9347},
  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}
}

@inproceedings{Szot2021Habitat2,
  title = {{Habitat 2.0: Training Home Assistants to Rearrange their Habitat}},
  author = {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},
  year = {2021},
  booktitle = {Advances in Neural Information Processing Systems},
  volume = {34},
  pages = {251--266},
  url = {https://proceedings.neurips.cc/paper_files/paper/2021/hash/021bbc7ee20b71134d53e20206bd6feb-Abstract.html}
}

@misc{Kolve2017AI2THOR,
  title = {{AI2-THOR: An Interactive 3D Environment for Visual AI}},
  author = {Kolve, Eric and Mottaghi, Roozbeh and Gordon, Daniel and Zhu, Yuke and Gupta, Abhinav and Farhadi, Ali},
  year = {2017},
  eprint = {1712.05474},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1712.05474v1}
}

@inproceedings{Deitke2022ProcTHOR,
  title = {{ProcTHOR: Large-Scale Embodied AI Using Procedural Generation}},
  author = {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},
  year = {2022},
  booktitle = {Advances in Neural Information Processing Systems},
  volume = {35},
  pages = {5982--5994},
  url = {https://proceedings.neurips.cc/paper_files/paper/2022/hash/27c546ab1e4f1d7d638e6a8dfbad9a07-Abstract-Conference.html}
}

@inproceedings{Xia2018Gibson,
  title = {{Gibson Env: Real-World Perception for Embodied Agents}},
  author = {Xia, Fei and Zamir, Amir R. and He, Zhiyang and Sax, Alexander and Malik, Jitendra and Savarese, Silvio},
  year = {2018},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages = {9068--9079},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Xia_Gibson_Env_Real-World_CVPR_2018_paper.html},
  doi = {10.1109/cvpr.2018.00945}
}

@inproceedings{Shen2021iGibson,
  title = {{iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes}},
  author = {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},
  year = {2021},
  booktitle = {2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  pages = {7520--7527},
  doi = {10.1109/iros51168.2021.9636667},
  url = {https://arxiv.org/abs/2012.02924}
}

@inproceedings{Li2022iGibson2,
  title = {{iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks}},
  author = {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},
  year = {2022},
  booktitle = {Conference on Robot Learning},
  url = {https://proceedings.mlr.press/v164/li22b.html}
}

@inproceedings{Deitke2020RoboTHOR,
  title = {{RoboTHOR: An Open Simulation-to-Real Embodied AI Platform}},
  author = {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},
  year = {2020},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {3164--3174},
  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}
}

@inproceedings{Xiang2020SAPIEN,
  title = {{SAPIEN: A SimulAted Part-Based Interactive ENvironment}},
  author = {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},
  year = {2020},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {11097--11107},
  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}
}

@inproceedings{Downs2022GSO,
  title = {{Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items}},
  author = {Downs, Laura and Francis, Anthony and Koenig, Nate and Kinman, Brandon and Hickman, Ryan and Reymann, Krista and McHugh, Thomas B. and Vanhoucke, Vincent},
  year = {2022},
  booktitle = {2022 International Conference on Robotics and Automation (ICRA)},
  doi = {10.1109/icra46639.2022.9811809},
  url = {https://arxiv.org/abs/2204.11918}
}

@inproceedings{Reizenstein2021CO3D,
  title = {{Common Objects in 3D: Large-Scale Learning and Evaluation of Real-Life 3D Category Reconstruction}},
  author = {Reizenstein, Jeremy and Shapovalov, Roman and Henzler, Philipp and Sbordone, Luca and Labatut, Patrick and Novotny, David},
  year = {2021},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages = {10901--10911},
  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}
}

@inproceedings{Srivastava2022BEHAVIOR,
  title = {{BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments}},
  author = {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},
  year = {2022},
  booktitle = {Conference on Robot Learning},
  url = {https://proceedings.mlr.press/v164/srivastava22a.html}
}

@inproceedings{Li2023BEHAVIOR1K,
  title = {{BEHAVIOR-1K: A Benchmark for Embodied AI with 1,000 Everyday Activities and Realistic Simulation}},
  author = {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},
  year = {2023},
  booktitle = {Conference on Robot Learning},
  url = {https://proceedings.mlr.press/v205/li23a.html}
}

@inproceedings{Gu2023ManiSkill2,
  title = {{ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills}},
  author = {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},
  year = {2023},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2302.04659}
}

@inproceedings{Grauman2022Ego4D,
  title = {{Ego4D: Around the World in 3,000 Hours of Egocentric Video}},
  author = {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},
  year = {2022},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {18995--19012},
  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}
}

@inproceedings{Grauman2024EgoExo4D,
  title = {{Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives}},
  author = {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},
  year = {2024},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {19383--19400},
  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}
}

@article{Milgram1994Taxonomy,
  title = {{A Taxonomy of Mixed Reality Visual Displays}},
  author = {Milgram, Paul and Kishino, Fumio},
  year = {1994},
  journal = {IEICE Transactions on Information and Systems},
  volume = {E77-D},
  pages = {1321--1329},
  url = {https://globals.ieice.org/en_transactions/information/10.1587/e77-d_12_1321/_p},
  number = {12}
}

@inproceedings{Song2015SUNRGBD,
  title = {{SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite}},
  author = {Song, Shuran and Lichtenberg, Samuel P. and Xiao, Jianxiong},
  year = {2015},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages = {567--576},
  doi = {10.1109/cvpr.2015.7298655},
  url = {https://openaccess.thecvf.com/content_cvpr_2015/html/Song_SUN_RGB-D_A_2015_CVPR_paper.html}
}

@inproceedings{Armeni2016S3DIS,
  title = {{3D Semantic Parsing of Large-Scale Indoor Spaces}},
  author = {Armeni, Iro and Sener, Ozan and Zamir, Amir R. and Jiang, Helen and Brilakis, Ioannis and Fischer, Martin and Savarese, Silvio},
  year = {2016},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages = {1534--1543},
  doi = {10.1109/cvpr.2016.170},
  url = {https://openaccess.thecvf.com/content_cvpr_2016/html/Armeni_3D_Semantic_Parsing_CVPR_2016_paper.html}
}

@inproceedings{Park2019DeepSDF,
  title = {{DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation}},
  author = {Jeong Joon Park and Peter Florence and Julian Straub and Richard Newcombe and Steven Lovegrove},
  year = {2019},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content_CVPR_2019/html/Park_DeepSDF_Learning_Continuous_Signed_Distance_Functions_for_Shape_Representation_CVPR_2019_paper.html},
  eprint = {1901.05103},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr.2019.00025}
}

@inproceedings{Mescheder2019Occupancy,
  title = {{Occupancy Networks: Learning 3D Reconstruction in Function Space}},
  author = {Lars Mescheder and Michael Oechsle and Michael Niemeyer and Sebastian Nowozin and Andreas Geiger},
  year = {2019},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content_CVPR_2019/html/Mescheder_Occupancy_Networks_Learning_3D_Reconstruction_in_Function_Space_CVPR_2019_paper.html},
  eprint = {1812.03828},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr.2019.00459}
}

@inproceedings{Peng2020ConvONet,
  title = {{Convolutional Occupancy Networks}},
  author = {Songyou Peng and Michael Niemeyer and Lars Mescheder and Marc Pollefeys and Andreas Geiger},
  year = {2020},
  booktitle = {Computer Vision -- ECCV},
  url = {https://pengsongyou.github.io/conv_onet},
  eprint = {2003.04618},
  archivePrefix = {arXiv},
  doi = {10.1007/978-3-030-58580-8_31}
}

@inproceedings{Sitzmann2020SIREN,
  title = {{Implicit Neural Representations with Periodic Activation Functions}},
  author = {Vincent Sitzmann and Julien N. P. Martel and Alexander W. Bergman and David B. Lindell and Gordon Wetzstein},
  year = {2020},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://www.vincentsitzmann.com/siren/},
  eprint = {2006.09661},
  archivePrefix = {arXiv},
}

@inproceedings{Tancik2020FourierFeatures,
  title = {{Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains}},
  author = {Matthew Tancik and Pratul P. Srinivasan and Ben Mildenhall and Sara Fridovich-Keil and Nithin Raghavan and Utkarsh Singhal and Ravi Ramamoorthi and Jonathan T. Barron and Ren Ng},
  year = {2020},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://bmild.github.io/fourfeat/},
  eprint = {2006.10739},
  archivePrefix = {arXiv},
}

@inproceedings{Wang2021NeuS,
  title = {{NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction}},
  author = {Peng Wang and Lingjie Liu and Yuan Liu and Christian Theobalt and Taku Komura and Wenping Wang},
  year = {2021},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://lingjie0206.github.io/papers/NeuS/},
  eprint = {2106.10689},
  archivePrefix = {arXiv},
}

@inproceedings{Yariv2021VolSDF,
  title = {{Volume Rendering of Neural Implicit Surfaces}},
  author = {Lior Yariv and Jiatao Gu and Yoni Kasten and Yaron Lipman},
  year = {2021},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://lioryariv.github.io/volsdf/},
  eprint = {2106.12052},
  archivePrefix = {arXiv},
}

@inproceedings{Yariv2020IDR,
  title = {{Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance}},
  author = {Lior Yariv and Yoni Kasten and Dror Moran and Meirav Galun and Matan Atzmon and Ronen Basri and Yaron Lipman},
  year = {2020},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://lioryariv.github.io/idr/},
  eprint = {2003.09852},
  archivePrefix = {arXiv},
}

@inproceedings{Chen2022TensoRF,
  title = {{TensoRF: Tensorial Radiance Fields}},
  author = {Anpei Chen and Zexiang Xu and Andreas Geiger and Jingyi Yu and Hao Su},
  year = {2022},
  booktitle = {Computer Vision -- ECCV},
  url = {https://apchenstu.github.io/TensoRF/},
  eprint = {2203.09517},
  archivePrefix = {arXiv},
  doi = {10.1007/978-3-031-19824-3_20}
}

@article{Mueller2022InstantNGP,
  title = {{Instant Neural Graphics Primitives with a Multiresolution Hash Encoding}},
  author = {Thomas Müller and Alex Evans and Christoph Schied and Alexander Keller},
  year = {2022},
  journal = {ACM Transactions on Graphics},
  volume = {41},
  number = {4},
  pages = {102:1--102:15},
  url = {https://arxiv.org/abs/2201.05989},
  eprint = {2201.05989},
  archivePrefix = {arXiv},
  doi = {10.1145/3528223.3530127},
}

@inproceedings{FridovichKeil2022Plenoxels,
  title = {{Plenoxels: Radiance Fields Without Neural Networks}},
  author = {Sara Fridovich-Keil and Alex Yu and Matthew Tancik and Qinhong Chen and Benjamin Recht and Angjoo Kanazawa},
  year = {2022},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2022/html/Fridovich-Keil_Plenoxels_Radiance_Fields_Without_Neural_Networks_CVPR_2022_paper.html},
  eprint = {2112.05131},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52688.2022.00542}
}

@inproceedings{Barron2021MipNeRF,
  title = {{Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields}},
  author = {Jonathan T. Barron and Ben Mildenhall and Matthew Tancik and Peter Hedman and Ricardo Martin-Brualla and Pratul P. Srinivasan},
  year = {2021},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  url = {https://openaccess.thecvf.com/content/ICCV2021/html/Barron_Mip-NeRF_A_Multiscale_Representation_for_Anti-Aliasing_Neural_Radiance_Fields_ICCV_2021_paper.html},
  eprint = {2103.13415},
  archivePrefix = {arXiv},
  doi = {10.1109/iccv48922.2021.00580}
}

@inproceedings{Barron2022MipNeRF360,
  title = {{Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields}},
  author = {Jonathan T. Barron and Ben Mildenhall and Dor Verbin and Pratul P. Srinivasan and Peter Hedman},
  year = {2022},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2022/html/Barron_Mip-NeRF_360_Unbounded_Anti-Aliased_Neural_Radiance_Fields_CVPR_2022_paper.html},
  eprint = {2111.12077},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52688.2022.00539}
}

@inproceedings{Barron2023ZipNeRF,
  title = {{Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields}},
  author = {Jonathan T. Barron and Ben Mildenhall and Dor Verbin and Pratul P. Srinivasan and Peter Hedman},
  year = {2023},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  url = {https://openaccess.thecvf.com/content/ICCV2023/html/Barron_Zip-NeRF_Anti-Aliased_Grid-Based_Neural_Radiance_Fields_ICCV_2023_paper.html},
  eprint = {2304.06706},
  archivePrefix = {arXiv},
  doi = {10.1109/iccv51070.2023.01804}
}

@inproceedings{Yu2021PixelNeRF,
  title = {{pixelNeRF: Neural Radiance Fields From One or Few Images}},
  author = {Alex Yu and Vickie Ye and Matthew Tancik and Angjoo Kanazawa},
  year = {2021},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2021/html/Yu_pixelNeRF_Neural_Radiance_Fields_From_One_or_Few_Images_CVPR_2021_paper.html},
  eprint = {2012.02190},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr46437.2021.00455}
}

@inproceedings{Wang2021IBRNet,
  title = {{IBRNet: Learning Multi-View Image-Based Rendering}},
  author = {Qianqian Wang and Zhicheng Wang and Kyle Genova and Pratul P. Srinivasan and Howard Zhou and Jonathan T. Barron and Ricardo Martin-Brualla and Noah Snavely and Thomas Funkhouser},
  year = {2021},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2021/html/Wang_IBRNet_Learning_Multi-View_Image-Based_Rendering_CVPR_2021_paper.html},
  eprint = {2102.13090},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr46437.2021.00466}
}

@inproceedings{Munkberg2022Nvdiffrec,
  title = {{Extracting Triangular 3D Models, Materials, and Lighting From Images}},
  author = {Jacob Munkberg and Jon Hasselgren and Tianchang Shen and Jun Gao and Wenzheng Chen and Alex Evans and Thomas Müller and Sanja Fidler},
  year = {2022},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2022/html/Munkberg_Extracting_Triangular_3D_Models_Materials_and_Lighting_From_Images_CVPR_2022_paper.html},
  eprint = {2111.12503},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52688.2022.00810}
}

@article{Zhang2021NeRFactor,
  title = {{NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination}},
  author = {Xiuming Zhang and Pratul P. Srinivasan and Boyang Deng and Paul Debevec and William T. Freeman and Jonathan T. Barron},
  year = {2021},
  journal = {ACM Transactions on Graphics},
  url = {https://xiuming.info/projects/nerfactor/},
  eprint = {2106.01970},
  archivePrefix = {arXiv},
  doi = {10.1145/3478513.3480496},
  volume = {40},
  number = {6},
}

@inproceedings{Verbin2022RefNeRF,
  title = {{Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields}},
  author = {Dor Verbin and Peter Hedman and Ben Mildenhall and Todd Zickler and Jonathan T. Barron and Pratul P. Srinivasan},
  year = {2022},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2022/html/Verbin_Ref-NeRF_Structured_View-Dependent_Appearance_for_Neural_Radiance_Fields_CVPR_2022_paper.html},
  eprint = {2112.03907},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52688.2022.00541}
}

@inproceedings{Huang2024TwoDGS,
  title = {{2D Gaussian Splatting for Geometrically Accurate Radiance Fields}},
  author = {Binbin Huang and Zehao Yu and Anpei Chen and Andreas Geiger and Shenghua Gao},
  year = {2024},
  booktitle = {SIGGRAPH Conference Papers},
  doi = {10.1145/3641519.3657428},
  url = {https://surfsplatting.github.io/},
  eprint = {2403.17888},
  archivePrefix = {arXiv},
}

@inproceedings{Guedon2024SuGaR,
  title = {{SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering}},
  author = {Antoine Guédon and Vincent Lepetit},
  year = {2024},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2024/html/Guedon_SuGaR_Surface-Aligned_Gaussian_Splatting_for_Efficient_3D_Mesh_Reconstruction_and_CVPR_2024_paper.html},
  eprint = {2311.12775},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52733.2024.00512}
}

@inproceedings{Yu2024MipSplatting,
  title = {{Mip-Splatting: Alias-free 3D Gaussian Splatting}},
  author = {Zehao Yu and Anpei Chen and Binbin Huang and Torsten Sattler and Andreas Geiger},
  year = {2024},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2024/html/Yu_Mip-Splatting_Alias-free_3D_Gaussian_Splatting_CVPR_2024_paper.html},
  eprint = {2311.16493},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52733.2024.01839}
}

@inproceedings{Lu2024ScaffoldGS,
  title = {{Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering}},
  author = {Tao Lu and Mulin Yu and Linning Xu and Yuanbo Xiangli and Limin Wang and Dahua Lin and Bo Dai},
  year = {2024},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2024/html/Lu_Scaffold-GS_Structured_3D_Gaussians_for_View-Adaptive_Rendering_CVPR_2024_paper.html},
  eprint = {2312.00109},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52733.2024.01952}
}

@inproceedings{Wu2016ThreeDGAN,
  title = {{Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling}},
  author = {Jiajun Wu and Chengkai Zhang and Tianfan Xue and William T. Freeman and Joshua B. Tenenbaum},
  year = {2016},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://proceedings.neurips.cc/paper_files/paper/2016/hash/44f683a84163b3523afe57c2e008bc8c-Abstract.html},
  eprint = {1610.07584},
  archivePrefix = {arXiv},
}

@inproceedings{Achlioptas2018PointClouds,
  title = {{Learning Representations and Generative Models for 3D Point Clouds}},
  author = {Panos Achlioptas and Olga Diamanti and Ioannis Mitliagkas and Leonidas Guibas},
  year = {2018},
  booktitle = {Proceedings of the International Conference on Machine Learning},
  volume = {80},
  pages = {40--49},
  url = {https://proceedings.mlr.press/v80/achlioptas18a.html},
  eprint = {1707.02392},
  archivePrefix = {arXiv},
}

@inproceedings{Yang2019PointFlow,
  title = {{PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows}},
  author = {Guandao Yang and Xun Huang and Zekun Hao and Ming-Yu Liu and Serge Belongie and Bharath Hariharan},
  year = {2019},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  url = {https://openaccess.thecvf.com/content_ICCV_2019/html/Yang_PointFlow_3D_Point_Cloud_Generation_With_Continuous_Normalizing_Flows_ICCV_2019_paper.html},
  eprint = {1906.12320},
  archivePrefix = {arXiv},
  doi = {10.1109/iccv.2019.00464}
}

@inproceedings{Groueix2018AtlasNet,
  title = {{A Papier-Mâché Approach to Learning 3D Surface Generation}},
  author = {Thibault Groueix and Matthew Fisher and Vladimir G. Kim and Bryan C. Russell and Mathieu Aubry},
  year = {2018},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Groueix_A_Papier-Mache_Approach_CVPR_2018_paper.html},
  eprint = {1802.05384},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr.2018.00030}
}

@inproceedings{Nash2020PolyGen,
  title = {{PolyGen: An Autoregressive Generative Model of 3D Meshes}},
  author = {Charlie Nash and Yaroslav Ganin and S. M. Ali Eslami and Peter Battaglia},
  year = {2020},
  booktitle = {Proceedings of the International Conference on Machine Learning},
  volume = {119},
  pages = {7220--7229},
  url = {https://proceedings.mlr.press/v119/nash20a.html},
  eprint = {2002.10880},
  archivePrefix = {arXiv},
}

@inproceedings{Shen2021DMTet,
  title = {{Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis}},
  author = {Tianchang Shen and Jun Gao and Kangxue Yin and Ming-Yu Liu and Sanja Fidler},
  year = {2021},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://proceedings.neurips.cc/paper_files/paper/2021/hash/30a237d18c50f563cba4531f1db44acf-Abstract.html},
  eprint = {2111.04276},
  archivePrefix = {arXiv},
}

@article{Shen2023FlexiCubes,
  title = {{Flexible Isosurface Extraction for Gradient-Based Mesh Optimization}},
  author = {Tianchang Shen and Jacob Munkberg and Jon Hasselgren and Kangxue Yin and Zian Wang and Wenzheng Chen and Zan Gojcic and Sanja Fidler and Nicholas Sharp and Jun Gao},
  year = {2023},
  journal = {ACM Transactions on Graphics},
  volume = {42},
  number = {4},
  pages = {37:1--37:16},
  doi = {10.1145/3592430},
  url = {https://research.nvidia.com/labs/toronto-ai/flexicubes/},
  eprint = {2308.05371},
  archivePrefix = {arXiv},
}

@inproceedings{Gao2022GET3D,
  title = {{GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images}},
  author = {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},
  year = {2022},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://proceedings.neurips.cc/paper_files/paper/2022/hash/cebbd24f1e50bcb63d015611fe0fe767-Abstract-Conference.html},
  eprint = {2209.11163},
  archivePrefix = {arXiv},
}

@inproceedings{Chan2022EG3D,
  title = {{Efficient Geometry-Aware 3D Generative Adversarial Networks}},
  author = {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},
  year = {2022},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2022/html/Chan_Efficient_Geometry-Aware_3D_Generative_Adversarial_Networks_CVPR_2022_paper.html},
  eprint = {2112.07945},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52688.2022.01565}
}

@inproceedings{Zeng2022LION,
  title = {{LION: Latent Point Diffusion Models for 3D Shape Generation}},
  author = {Xiaohui Zeng and Arash Vahdat and Francis Williams and Zan Gojcic and Or Litany and Sanja Fidler and Karsten Kreis},
  year = {2022},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://proceedings.neurips.cc/paper_files/paper/2022/hash/40e56dabe12095a5fc44a6e4c3835948-Abstract-Conference.html},
  eprint = {2210.06978},
  archivePrefix = {arXiv},
}

@inproceedings{Cheng2023SDFusion,
  title = {{SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation}},
  author = {Yen-Chi Cheng and Hsin-Ying Lee and Sergey Tulyakov and Alexander G. Schwing and Liang-Yan Gui},
  year = {2023},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2023/html/Cheng_SDFusion_Multimodal_3D_Shape_Completion_Reconstruction_and_Generation_CVPR_2023_paper.html},
  eprint = {2212.04493},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52729.2023.00433}
}

@inproceedings{Liu2023MeshDiffusion,
  title = {{MeshDiffusion: Score-based Generative 3D Mesh Modeling}},
  author = {Zhen Liu and Yao Feng and Michael J. Black and Derek Nowrouzezahrai and Liam Paull and Weiyang Liu},
  year = {2023},
  booktitle = {International Conference on Learning Representations},
  url = {https://meshdiffusion.github.io/},
  eprint = {2303.08133},
  archivePrefix = {arXiv},
}

@inproceedings{Siddiqui2024MeshGPT,
  title = {{MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers}},
  author = {Yawar Siddiqui and Antonio Alliegro and Alexey Artemov and Tatiana Tommasi and Daniele Sirigatti and Vladislav Rosov and Angela Dai and Matthias Nießner},
  year = {2024},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2024/html/Siddiqui_MeshGPT_Generating_Triangle_Meshes_with_Decoder-Only_Transformers_CVPR_2024_paper.html},
  eprint = {2311.15475},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52733.2024.01855}
}

@inproceedings{Chen2025MeshAnything,
  title = {{MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers}},
  author = {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},
  year = {2025},
  booktitle = {International Conference on Learning Representations},
  url = {https://proceedings.iclr.cc/paper_files/paper/2025/hash/7fc69f53a6ca2664ef23a9597903ca6f-Abstract-Conference.html},
  eprint = {2406.10163},
  archivePrefix = {arXiv},
}

@inproceedings{Jain2022DreamFields,
  title = {{Zero-Shot Text-Guided Object Generation With Dream Fields}},
  author = {Ajay Jain and Ben Mildenhall and Jonathan T. Barron and Pieter Abbeel and Ben Poole},
  year = {2022},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2022/html/Jain_Zero-Shot_Text-Guided_Object_Generation_With_Dream_Fields_CVPR_2022_paper.html},
  eprint = {2112.01455},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52688.2022.00094}
}

@inproceedings{Michel2022Text2Mesh,
  title = {{Text2Mesh: Text-Driven Neural Stylization for Meshes}},
  author = {Oscar Michel and Roi Bar-On and Richard Liu and Sagie Benaim and Rana Hanocka},
  year = {2022},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2022/html/Michel_Text2Mesh_Text-Driven_Neural_Stylization_for_Meshes_CVPR_2022_paper.html},
  eprint = {2112.03221},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52688.2022.01313}
}

@inproceedings{Khalid2022CLIPMesh,
  title = {{CLIP-Mesh: Generating textured meshes from text using pretrained image-text models}},
  author = {Mohammad Khalid, Nasir and Xie, Tianhao and Belilovsky, Eugene and Popa, Tiberiu},
  year = {2022},
  booktitle = {SIGGRAPH Asia Conference Papers},
  pages = {25:1--25:8},
  doi = {10.1145/3550469.3555392},
  url = {https://doi.org/10.1145/3550469.3555392},
  eprint = {2203.13333},
  archivePrefix = {arXiv},
}

@inproceedings{Qian2024Magic123,
  title = {{Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors}},
  author = {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},
  year = {2024},
  booktitle = {International Conference on Learning Representations},
  url = {https://guochengqian.github.io/project/magic123/},
  eprint = {2306.17843},
  archivePrefix = {arXiv},
}

@inproceedings{Liu2023One2345,
  title = {{One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization}},
  author = {Minghua Liu and Chao Xu and Haian Jin and Linghao Chen and Mukund Varma T and Zexiang Xu and Hao Su},
  year = {2023},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://proceedings.neurips.cc/paper_files/paper/2023/hash/4683beb6bab325650db13afd05d1a14a-Abstract-Conference.html},
  eprint = {2306.16928},
  archivePrefix = {arXiv},
}

@inproceedings{Liu2024One2345Plus,
  title = {{One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion}},
  author = {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},
  year = {2024},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  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},
  eprint = {2311.07885},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52733.2024.00960}
}

@inproceedings{Long2024Wonder3D,
  title = {{Wonder3D: Single Image to 3D using Cross-Domain Diffusion}},
  author = {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},
  year = {2024},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2024/html/Long_Wonder3D_Single_Image_to_3D_using_Cross-Domain_Diffusion_CVPR_2024_paper.html},
  eprint = {2310.15008},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52733.2024.00951}
}

@misc{Shi2023Zero123Plus,
  title = {{Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model}},
  author = {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},
  year = {2023},
  howpublished = {arXiv preprint arXiv:2310.15110},
  url = {https://arxiv.org/abs/2310.15110},
  eprint = {2310.15110},
  archivePrefix = {arXiv},
}

@inproceedings{Wu2024Unique3D,
  title = {{Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image}},
  author = {Kailu Wu and Fangfu Liu and Zhihan Cai and Runjie Yan and Hanyang Wang and Yating Hu and Yueqi Duan and Kaisheng Ma},
  year = {2024},
  booktitle = {Advances in Neural Information Processing Systems},
  doi = {10.52202/079017-3974},
  url = {https://proceedings.neurips.cc/paper_files/paper/2024/hash/e25198b6a75f74277ee3a2bd4165d9ef-Abstract-Conference.html},
  eprint = {2405.20343},
  archivePrefix = {arXiv},
}

@inproceedings{Chen2023Text2Tex,
  title = {{Text2Tex: Text-driven Texture Synthesis via Diffusion Models}},
  author = {Dave Zhenyu Chen and Yawar Siddiqui and Hsin-Ying Lee and Sergey Tulyakov and Matthias Nießner},
  year = {2023},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  url = {https://openaccess.thecvf.com/content/ICCV2023/html/Chen_Text2Tex_Text-driven_Texture_Synthesis_via_Diffusion_Models_ICCV_2023_paper.html},
  eprint = {2303.11396},
  archivePrefix = {arXiv},
  doi = {10.1109/iccv51070.2023.01701}
}

@inproceedings{Zeng2024Paint3D,
  title = {{Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models}},
  author = {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},
  year = {2024},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2024/html/Zeng_Paint3D_Paint_Anything_3D_with_Lighting-Less_Texture_Diffusion_Models_CVPR_2024_paper.html},
  eprint = {2312.13913},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52733.2024.00407}
}

@article{Lorensen1987MarchingCubes,
  title = {{Marching cubes: A high resolution 3D surface construction algorithm}},
  author = {William E. Lorensen and Harvey E. Cline},
  year = {1987},
  journal = {ACM SIGGRAPH Computer Graphics},
  volume = {21},
  number = {4},
  pages = {163--169},
  doi = {10.1145/37402.37422},
  url = {https://graphics.stanford.edu/courses/cs348a-21-winter/Papers/Marching_Cubes.pdf},
}

@inproceedings{Curless1996VolumetricFusion,
  title = {{A volumetric method for building complex models from range images}},
  author = {Brian Curless and Marc Levoy},
  year = {1996},
  booktitle = {Proceedings of the 23rd annual conference on Computer graphics and interactive techniques},
  pages = {303--312},
  doi = {10.1145/237170.237269},
  url = {https://www.cs.cmu.edu/~seitz/course/SIGG99/papers/curl96.pdf},
}

@article{Kajiya1986RenderingEquation,
  title = {{The rendering equation}},
  author = {James T. Kajiya},
  year = {1986},
  journal = {ACM SIGGRAPH Computer Graphics},
  volume = {20},
  number = {4},
  pages = {143--150},
  doi = {10.1145/15886.15902},
  url = {https://doi.org/10.1145/15886.15902},
}

@article{Cook1982Reflectance,
  title = {{A Reflectance Model for Computer Graphics}},
  author = {R. L. Cook and K. E. Torrance},
  year = {1982},
  journal = {ACM Transactions on Graphics},
  volume = {1},
  number = {1},
  pages = {7--24},
  doi = {10.1145/357290.357293},
  url = {https://www.graphics.cornell.edu/~westin/consortium-home/cook-tog.pdf},
}

@article{Hart1996SphereTracing,
  title = {{Sphere tracing: a geometric method for the antialiased ray tracing of implicit surfaces}},
  author = {John C. Hart},
  year = {1996},
  journal = {The Visual Computer},
  volume = {12},
  number = {10},
  pages = {527--545},
  doi = {10.1007/s003710050084},
  url = {https://experts.illinois.edu/en/publications/sphere-tracing-a-geometric-method-for-the-antialiased-ray-tracing/},
}

@inproceedings{Parish2001ProceduralCities,
  title = {{Procedural modeling of cities}},
  author = {Yoav I. H. Parish and Pascal Müller},
  year = {2001},
  booktitle = {Proceedings of the 28th annual conference on Computer graphics and interactive techniques},
  pages = {301--308},
  doi = {10.1145/383259.383292},
  url = {https://people.eecs.berkeley.edu/~sequin/CS285/PAPERS/Parish_Muller01.pdf},
}

@article{Mueller2006ProceduralBuildings,
  title = {{Procedural modeling of buildings}},
  author = {Pascal Müller and Peter Wonka and Simon Haegler and Andreas Ulmer and Luc Van Gool},
  year = {2006},
  journal = {ACM Transactions on Graphics},
  volume = {25},
  number = {3},
  pages = {614--623},
  doi = {10.1145/1141911.1141931},
  url = {https://doi.org/10.1145/1141911.1141931},
}

@article{Merrell2010ResidentialLayouts,
  title = {{Computer-generated residential building layouts}},
  author = {Paul Merrell and Eric Schkufza and Vladlen Koltun},
  year = {2010},
  journal = {ACM Transactions on Graphics},
  volume = {29},
  number = {6},
  pages = {1--12},
  doi = {10.1145/1882261.1866203},
  url = {https://doi.org/10.1145/1882261.1866203},
}

@article{Fisher2012SceneSynthesis,
  title = {{Example-based synthesis of 3D object arrangements}},
  author = {Matthew Fisher and Daniel Ritchie and Manolis Savva and Thomas Funkhouser and Pat Hanrahan},
  year = {2012},
  journal = {ACM Transactions on Graphics},
  volume = {31},
  number = {6},
  pages = {1--11},
  doi = {10.1145/2366145.2366154},
  url = {https://pixl.cs.princeton.edu/pubs/Fisher_2012_ESO/},
}

@article{Wang2018DeepScenePriors,
  title = {{Deep convolutional priors for indoor scene synthesis}},
  author = {Kai Wang and Manolis Savva and Angel X. Chang and Daniel Ritchie},
  year = {2018},
  journal = {ACM Transactions on Graphics},
  volume = {37},
  number = {4},
  pages = {1--14},
  doi = {10.1145/3197517.3201362},
  url = {https://doi.org/10.1145/3197517.3201362},
}

@article{Wang2019PlanIT,
  title = {{PlanIT: Planning and Instantiating Indoor Scenes with Relation Graph and Spatial Prior Networks}},
  author = {Kai Wang and Yu-An Lin and Ben Weissmann and Manolis Savva and Angel X. Chang and Daniel Ritchie},
  year = {2019},
  journal = {ACM Transactions on Graphics},
  volume = {38},
  number = {4},
  pages = {1--15},
  doi = {10.1145/3306346.3322941},
  url = {https://doi.org/10.1145/3306346.3322941},
}

@inproceedings{Kazhdan2006Poisson,
  title = {{Poisson Surface Reconstruction}},
  author = {Michael Kazhdan and Matthew Bolitho and Hugues Hoppe},
  year = {2006},
  booktitle = {Eurographics Symposium on Geometry Processing},
  pages = {61--70},
  doi = {10.2312/SGP/SGP06/061-070},
  url = {https://hhoppe.com/poissonrecon.pdf},
}

@inproceedings{Kato2018NeuralMeshRenderer,
  title = {{Neural 3D Mesh Renderer}},
  author = {Hiroharu Kato and Yoshitaka Ushiku and Tatsuya Harada},
  year = {2018},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Kato_Neural_3D_Mesh_CVPR_2018_paper.html},
  eprint = {1711.07566},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr.2018.00411}
}

@inproceedings{Dhamo2021GraphTo3D,
  title = {{Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs}},
  author = {Helisa Dhamo and Fabian Manhardt and Nassir Navab and Federico Tombari},
  year = {2021},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  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},
  eprint = {2108.08841},
  archivePrefix = {arXiv},
  doi = {10.1109/iccv48922.2021.01604}
}

@inproceedings{Zhai2024EchoScene,
  title = {{EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion}},
  author = {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},
  year = {2024},
  booktitle = {Computer Vision -- ECCV},
  doi = {10.1007/978-3-031-72664-4_10},
  url = {https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/3146_ECCV_2024_paper.php},
  eprint = {2405.00915},
  archivePrefix = {arXiv},
}

@article{Li2019GRAINS,
  title = {{GRAINS: Generative Recursive Autoencoders for INdoor Scenes}},
  author = {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},
  year = {2019},
  journal = {ACM Transactions on Graphics},
  volume = {38},
  number = {2},
  doi = {10.1145/3303766},
  url = {https://doi.org/10.1145/3303766},
  eprint = {1807.09193},
  archivePrefix = {arXiv},
}

@inproceedings{Raistrick2023Infinigen,
  title = {{Infinite Photorealistic Worlds using Procedural Generation}},
  author = {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},
  year = {2023},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2023/html/Raistrick_Infinite_Photorealistic_Worlds_Using_Procedural_Generation_CVPR_2023_paper.html},
  eprint = {2306.09310},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52729.2023.01215}
}

@inproceedings{Raistrick2024InfinigenIndoors,
  title = {{Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation}},
  author = {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},
  year = {2024},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2024/html/Raistrick_Infinigen_Indoors_Photorealistic_Indoor_Scenes_using_Procedural_Generation_CVPR_2024_paper.html},
  eprint = {2406.11824},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52733.2024.02058}
}

@article{Zhang2024Text2NeRF,
  title = {{Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields}},
  author = {Jingbo Zhang and Xiaoyu Li and Ziyu Wan and Can Wang and Jing Liao},
  year = {2024},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  volume = {30},
  number = {12},
  pages = {7749--7762},
  doi = {10.1109/TVCG.2024.3361502},
  url = {https://scholars.cityu.edu.hk/en/publications/text2nerf-text-driven-3d-scene-generation-with-neural-radiance-fi/},
  eprint = {2305.11588},
  archivePrefix = {arXiv},
}

@inproceedings{Chen2024SceneTex,
  title = {{SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors}},
  author = {Dave Zhenyu Chen and Haoxuan Li and Hsin-Ying Lee and Sergey Tulyakov and Matthias Nießner},
  year = {2024},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2024/html/Chen_SceneTex_High-Quality_Texture_Synthesis_for_Indoor_Scenes_via_Diffusion_Priors_CVPR_2024_paper.html},
  eprint = {2311.17261},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52733.2024.01992}
}

@inproceedings{Engstler2025SynCity,
  title = {{SynCity: Training-Free Generation of 3D Worlds}},
  author = {Paul Engstler and Aleksandar Shtedritski and Iro Laina and Christian Rupprecht and Andrea Vedaldi},
  year = {2025},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  url = {https://openaccess.thecvf.com/content/ICCV2025/html/Engstler_SynCity_Training-Free_Generation_of_3D_Worlds_ICCV_2025_paper.html},
  eprint = {2503.16420},
  archivePrefix = {arXiv},
  doi = {10.1109/iccv51701.2025.02561}
}

@inproceedings{Fang2025CtrlRoom,
  title = {{Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints}},
  author = {Chuan Fang and Yuan Dong and Kunming Luo and Xiaotao Hu and Rakesh Shrestha and Ping Tan},
  year = {2025},
  booktitle = {International Conference on 3D Vision},
  pages = {692--701},
  doi = {10.1109/3DV66043.2025.00069},
  url = {https://doi.org/10.1109/3DV66043.2025.00069},
  eprint = {2310.03602},
  archivePrefix = {arXiv},
}

@inproceedings{Kingma2014VAE,
  author = {Kingma, Diederik P and Welling, Max},
  title = {{Auto-Encoding Variational Bayes}},
  year = {2014},
  booktitle = {International Conference on Learning Representations},
  url = {https://iclr.cc/archive/2014/old-site/conference-proceedings.html},
  eprint = {1312.6114},
  archivePrefix = {arXiv}
}

@inproceedings{Rezende2014StochasticBackprop,
  author = {Rezende, Danilo Jimenez and Mohamed, Shakir and Wierstra, Daan},
  title = {{Stochastic Backpropagation and Approximate Inference in Deep Generative Models}},
  year = {2014},
  booktitle = {International Conference on Machine Learning},
  url = {https://arxiv.org/abs/1401.4082},
  eprint = {1401.4082},
  archivePrefix = {arXiv}
}

@inproceedings{Goodfellow2014GAN,
  author = {Goodfellow, Ian J. and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua},
  title = {{Generative Adversarial Nets}},
  year = {2014},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://proceedings.neurips.cc/paper_files/paper/2014/hash/f033ed80deb0234979a61f95710dbe25-Abstract.html},
  eprint = {1406.2661},
  archivePrefix = {arXiv},
  volume = {27}
}

@article{Mirza2014ConditionalGAN,
  author = {Mirza, Mehdi and Osindero, Simon},
  title = {{Conditional Generative Adversarial Nets}},
  year = {2014},
  journal = {arXiv preprint arXiv:1411.1784},
  url = {https://arxiv.org/abs/1411.1784},
  eprint = {1411.1784},
  archivePrefix = {arXiv}
}

@inproceedings{Karras2019StyleGAN,
  author = {Karras, Tero and Laine, Samuli and Aila, Timo},
  title = {{A Style-Based Generator Architecture for Generative Adversarial Networks}},
  year = {2019},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://arxiv.org/abs/1812.04948},
  eprint = {1812.04948},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr.2019.00453}
}

@inproceedings{Dinh2017RealNVP,
  author = {Dinh, Laurent and Sohl-Dickstein, Jascha and Bengio, Samy},
  title = {{Density estimation using Real NVP}},
  year = {2017},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/1605.08803},
  eprint = {1605.08803},
  archivePrefix = {arXiv}
}

@inproceedings{Oord2016PixelRNN,
  author = {van den Oord, A{\"a}ron and Kalchbrenner, Nal and Kavukcuoglu, Koray},
  title = {{Pixel Recurrent Neural Networks}},
  year = {2016},
  booktitle = {International Conference on Machine Learning},
  url = {https://arxiv.org/abs/1601.06759},
  eprint = {1601.06759},
  archivePrefix = {arXiv}
}

@inproceedings{Vaswani2017Transformer,
  author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N. and Kaiser, {\L}ukasz and Polosukhin, Illia},
  title = {{Attention Is All You Need}},
  year = {2017},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://arxiv.org/abs/1706.03762},
  eprint = {1706.03762},
  archivePrefix = {arXiv}
}

@inproceedings{Oord2017VQVAE,
  author = {van den Oord, Aaron and Vinyals, Oriol and Kavukcuoglu, Koray},
  title = {{Neural Discrete Representation Learning}},
  year = {2017},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://arxiv.org/abs/1711.00937},
  eprint = {1711.00937},
  archivePrefix = {arXiv}
}

@inproceedings{Esser2021VQGAN,
  author = {Esser, Patrick and Rombach, Robin and Ommer, Bj{\"o}rn},
  title = {{Taming Transformers for High-Resolution Image Synthesis}},
  year = {2021},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2021/html/Esser_Taming_Transformers_for_High-Resolution_Image_Synthesis_CVPR_2021_paper.html},
  eprint = {2012.09841},
  archivePrefix = {arXiv},
  pages = {12873--12883},
  doi = {10.1109/cvpr46437.2021.01268}
}

@inproceedings{Chang2022MaskGIT,
  author = {Chang, Huiwen and Zhang, Han and Jiang, Lu and Liu, Ce and Freeman, William T.},
  title = {{MaskGIT: Masked Generative Image Transformer}},
  year = {2022},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2022/html/Chang_MaskGIT_Masked_Generative_Image_Transformer_CVPR_2022_paper.html},
  eprint = {2202.04200},
  archivePrefix = {arXiv},
  pages = {11315--11325},
  doi = {10.1109/cvpr52688.2022.01103}
}

@inproceedings{Li2024MAR,
  author = {Li, Tianhong and Tian, Yonglong and Li, He and Deng, Mingyang and He, Kaiming},
  title = {{Autoregressive Image Generation without Vector Quantization}},
  year = {2024},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://arxiv.org/abs/2406.11838},
  eprint = {2406.11838},
  archivePrefix = {arXiv}
}

@inproceedings{SohlDickstein2015Diffusion,
  author = {Sohl-Dickstein, Jascha and Weiss, Eric A. and Maheswaranathan, Niru and Ganguli, Surya},
  title = {{Deep Unsupervised Learning using Nonequilibrium Thermodynamics}},
  year = {2015},
  booktitle = {International Conference on Machine Learning},
  url = {https://arxiv.org/abs/1503.03585},
  eprint = {1503.03585},
  archivePrefix = {arXiv}
}

@inproceedings{Ho2020DDPM,
  author = {Ho, Jonathan and Jain, Ajay and Abbeel, Pieter},
  title = {{Denoising Diffusion Probabilistic Models}},
  year = {2020},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://arxiv.org/abs/2006.11239},
  eprint = {2006.11239},
  archivePrefix = {arXiv}
}

@inproceedings{Song2021SDE,
  author = {Song, Yang and Sohl-Dickstein, Jascha and Kingma, Diederik P. and Kumar, Abhishek and Ermon, Stefano and Poole, Ben},
  title = {{Score-Based Generative Modeling through Stochastic Differential Equations}},
  year = {2021},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2011.13456},
  eprint = {2011.13456},
  archivePrefix = {arXiv}
}

@inproceedings{Song2021DDIM,
  author = {Song, Jiaming and Meng, Chenlin and Ermon, Stefano},
  title = {{Denoising Diffusion Implicit Models}},
  year = {2021},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2010.02502},
  eprint = {2010.02502},
  archivePrefix = {arXiv}
}

@inproceedings{Dhariwal2021GuidedDiffusion,
  author = {Dhariwal, Prafulla and Nichol, Alexander},
  title = {{Diffusion Models Beat GANs on Image Synthesis}},
  year = {2021},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://proceedings.neurips.cc/paper/2021/hash/49ad23d1ec9fa4bd8d77d02681df5cfa-Abstract.html},
  eprint = {2105.05233},
  archivePrefix = {arXiv},
  volume = {34},
  pages = {8780--8794}
}

@article{Ho2022CFG,
  author = {Ho, Jonathan and Salimans, Tim},
  title = {{Classifier-Free Diffusion Guidance}},
  year = {2022},
  journal = {arXiv preprint arXiv:2207.12598},
  url = {https://arxiv.org/abs/2207.12598},
  eprint = {2207.12598},
  archivePrefix = {arXiv}
}

@inproceedings{Lu2022DPMSolver,
  author = {Lu, Cheng and Zhou, Yuhao and Bao, Fan and Chen, Jianfei and Li, Chongxuan and Zhu, Jun},
  title = {{DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps}},
  year = {2022},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://arxiv.org/abs/2206.00927},
  eprint = {2206.00927},
  archivePrefix = {arXiv}
}

@inproceedings{Salimans2022ProgressiveDistillation,
  author = {Salimans, Tim and Ho, Jonathan},
  title = {{Progressive Distillation for Fast Sampling of Diffusion Models}},
  year = {2022},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2202.00512},
  eprint = {2202.00512},
  archivePrefix = {arXiv}
}

@inproceedings{Song2023Consistency,
  author = {Song, Yang and Dhariwal, Prafulla and Chen, Mark and Sutskever, Ilya},
  title = {{Consistency Models}},
  year = {2023},
  booktitle = {International Conference on Machine Learning},
  url = {https://arxiv.org/abs/2303.01469},
  eprint = {2303.01469},
  archivePrefix = {arXiv}
}

@inproceedings{Peebles2023DiT,
  author = {Peebles, William and Xie, Saining},
  title = {{Scalable Diffusion Models with Transformers}},
  year = {2023},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  url = {https://openaccess.thecvf.com/content/ICCV2023/html/Peebles_Scalable_Diffusion_Models_with_Transformers_ICCV_2023_paper.html},
  eprint = {2212.09748},
  archivePrefix = {arXiv},
  pages = {4195--4205},
  doi = {10.1109/iccv51070.2023.00387}
}

@inproceedings{Lipman2023FlowMatching,
  author = {Lipman, Yaron and Chen, Ricky T. Q. and Ben-Hamu, Heli and Nickel, Maximilian and Le, Matt},
  title = {{Flow Matching for Generative Modeling}},
  year = {2023},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2210.02747},
  eprint = {2210.02747},
  archivePrefix = {arXiv}
}

@inproceedings{Liu2023RectifiedFlow,
  author = {Liu, Xingchao and Gong, Chengyue and Liu, Qiang},
  title = {{Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow}},
  year = {2023},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2209.03003},
  eprint = {2209.03003},
  archivePrefix = {arXiv}
}

@inproceedings{Esser2024SD3,
  author = {Esser, Patrick and Kulal, Sumith and Blattmann, Andreas and Entezari, Rahim and M{\"u}ller, Jonas and Saini, Harry and Levi, Yam and Lorenz, Dominik and Sauer, Axel and Boesel, Frederic and Podell, Dustin and Dockhorn, Tim and English, Zion and Lacey, Kyle and Goodwin, Alex and Marek, Yannik and Rombach, Robin},
  title = {{Scaling Rectified Flow Transformers for High-Resolution Image Synthesis}},
  year = {2024},
  booktitle = {International Conference on Machine Learning},
  url = {https://proceedings.mlr.press/v235/esser24a.html},
  eprint = {2403.03206},
  archivePrefix = {arXiv},
  pages = {12606--12633}
}

@inproceedings{Saharia2022Imagen,
  author = {Saharia, Chitwan and Chan, William and Saxena, Saurabh and Li, Lala and Whang, Jay and Denton, Emily L. and Ghasemipour, Kamyar and Gontijo Lopes, Raphael and Karagol Ayan, Burcu and Salimans, Tim and Ho, Jonathan and Fleet, David and Norouzi, Mohammad},
  title = {{Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding}},
  year = {2022},
  booktitle = {Advances in Neural Information Processing Systems},
  doi = {10.52202/068431-2643},
  url = {https://proceedings.neurips.cc/paper_files/paper/2022/hash/ec795aeadae0b7d230fa35cbaf04c041-Abstract-Conference.html},
  eprint = {2205.11487},
  archivePrefix = {arXiv},
  volume = {35},
  pages = {36479--36494}
}

@inproceedings{Ho2022VideoDiffusion,
  author = {Ho, Jonathan and Salimans, Tim and Gritsenko, Alexey and Chan, William and Norouzi, Mohammad and Fleet, David J.},
  title = {{Video Diffusion Models}},
  year = {2022},
  booktitle = {Advances in Neural Information Processing Systems},
  doi = {10.52202/068431-0628},
  url = {https://proceedings.neurips.cc/paper_files/paper/2022/hash/39235c56aef13fb05a6adc95eb9d8d66-Abstract-Conference.html},
  eprint = {2204.03458},
  archivePrefix = {arXiv},
  volume = {35},
  pages = {8633--8646}
}

@article{Ho2022ImagenVideo,
  author = {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},
  title = {{Imagen Video: High Definition Video Generation with Diffusion Models}},
  year = {2022},
  journal = {arXiv preprint arXiv:2210.02303},
  url = {https://arxiv.org/abs/2210.02303},
  eprint = {2210.02303},
  archivePrefix = {arXiv}
}

@inproceedings{Singer2023MakeAVideo,
  author = {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},
  title = {{Make-A-Video: Text-to-Video Generation without Text-Video Data}},
  year = {2023},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2209.14792},
  eprint = {2209.14792},
  archivePrefix = {arXiv}
}

@inproceedings{Blattmann2023VideoLDM,
  author = {Blattmann, Andreas and Rombach, Robin and Ling, Huan and Dockhorn, Tim and Kim, Seung Wook and Fidler, Sanja and Kreis, Karsten},
  title = {{Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models}},
  year = {2023},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://arxiv.org/abs/2304.08818},
  eprint = {2304.08818},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52729.2023.02161}
}

@article{Blattmann2023SVD,
  author = {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},
  title = {{Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets}},
  year = {2023},
  journal = {arXiv preprint arXiv:2311.15127},
  url = {https://arxiv.org/abs/2311.15127},
  eprint = {2311.15127},
  archivePrefix = {arXiv}
}

@inproceedings{Chen2024VideoCrafter2,
  author = {Chen, Haoxin and Zhang, Yong and Cun, Xiaodong and Xia, Menghan and Wang, Xintao and Weng, Chao and Shan, Ying},
  title = {{VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models}},
  year = {2024},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2024/html/Chen_VideoCrafter2_Overcoming_Data_Limitations_for_High-Quality_Video_Diffusion_Models_CVPR_2024_paper.html},
  eprint = {2401.09047},
  archivePrefix = {arXiv},
  pages = {7310--7320},
  doi = {10.1109/cvpr52733.2024.00698}
}

@inproceedings{Guo2024AnimateDiff,
  author = {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},
  title = {{AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning}},
  year = {2024},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2307.04725},
  eprint = {2307.04725},
  archivePrefix = {arXiv}
}

@inproceedings{BarTal2024Lumiere,
  author = {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},
  title = {{Lumiere: A Space-Time Diffusion Model for Video Generation}},
  year = {2024},
  booktitle = {SIGGRAPH Asia 2024 Conference Papers},
  doi = {10.1145/3680528.3687614},
  url = {https://doi.org/10.1145/3680528.3687614},
  eprint = {2401.12945},
  archivePrefix = {arXiv},
  pages = {1--11}
}

@inproceedings{Kondratyuk2024VideoPoet,
  author = {Kondratyuk, Dan and Yu, Lijun and Gu, Xiuye and Lezama, Jos{\'e} 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},
  title = {{VideoPoet: A Large Language Model for Zero-Shot Video Generation}},
  year = {2024},
  booktitle = {International Conference on Machine Learning},
  url = {https://arxiv.org/abs/2312.14125},
  eprint = {2312.14125},
  archivePrefix = {arXiv}
}

@inproceedings{Hong2023CogVideo,
  author = {Hong, Wenyi and Ding, Ming and Zheng, Wendi and Liu, Xinghan and Tang, Jie},
  title = {{CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers}},
  year = {2023},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2205.15868},
  eprint = {2205.15868},
  archivePrefix = {arXiv}
}

@article{Kong2024HunyuanVideo,
  author = {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},
  title = {{HunyuanVideo: A Systematic Framework For Large Video Generative Models}},
  year = {2024},
  journal = {arXiv preprint arXiv:2412.03603},
  url = {https://arxiv.org/abs/2412.03603},
  eprint = {2412.03603},
  archivePrefix = {arXiv}
}

@article{Wan2025Wan,
  author = {{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},
  title = {{Wan: Open and Advanced Large-Scale Video Generative Models}},
  year = {2025},
  journal = {arXiv preprint arXiv:2503.20314},
  url = {https://arxiv.org/abs/2503.20314},
  eprint = {2503.20314},
  archivePrefix = {arXiv}
}

@article{Polyak2024MovieGen,
  author = {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},
  title = {{Movie Gen: A Cast of Media Foundation Models}},
  year = {2024},
  journal = {arXiv preprint arXiv:2410.13720},
  url = {https://arxiv.org/abs/2410.13720},
  eprint = {2410.13720},
  archivePrefix = {arXiv}
}

@article{Yan2021VideoGPT,
  author = {Yan, Wilson and Zhang, Yunzhi and Abbeel, Pieter and Srinivas, Aravind},
  title = {{VideoGPT: Video Generation using VQ-VAE and Transformers}},
  year = {2021},
  journal = {arXiv preprint arXiv:2104.10157},
  url = {https://arxiv.org/abs/2104.10157},
  eprint = {2104.10157},
  archivePrefix = {arXiv}
}

@inproceedings{Villegas2023Phenaki,
  author = {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},
  title = {{Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions}},
  year = {2023},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2210.02399},
  eprint = {2210.02399},
  archivePrefix = {arXiv}
}

@inproceedings{Yu2023MAGVIT,
  author = {Yu, Lijun and Cheng, Yong and Sohn, Kihyuk and Lezama, Jos{\'e} and Zhang, Han and Chang, Huiwen and Hauptmann, Alexander G. and Yang, Ming-Hsuan and Hao, Yuan and Essa, Irfan and Jiang, Lu},
  title = {{MAGVIT: Masked Generative Video Transformer}},
  year = {2023},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://arxiv.org/abs/2212.05199},
  eprint = {2212.05199},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52729.2023.01008}
}

@inproceedings{Deng2025NOVA,
  author = {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},
  title = {{Autoregressive Video Generation without Vector Quantization}},
  year = {2025},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2412.14169},
  eprint = {2412.14169},
  archivePrefix = {arXiv}
}

@article{Teng2025MAGI1,
  author = {{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},
  title = {{MAGI-1: Autoregressive Video Generation at Scale}},
  year = {2025},
  journal = {arXiv preprint arXiv:2505.13211},
  url = {https://arxiv.org/abs/2505.13211},
  eprint = {2505.13211},
  archivePrefix = {arXiv}
}

@inproceedings{Chen2024DiffusionForcing,
  author = {Chen, Boyuan and Mart{\'i} Mons{\'o}, Diego and Du, Yilun and Simchowitz, Max and Tedrake, Russ and Sitzmann, Vincent},
  title = {{Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion}},
  year = {2024},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://arxiv.org/abs/2407.01392},
  eprint = {2407.01392},
  archivePrefix = {arXiv}
}

@inproceedings{Song2025HistoryGuidance,
  author = {Song, Kiwhan and Chen, Boyuan and Simchowitz, Max and Du, Yilun and Tedrake, Russ and Sitzmann, Vincent},
  title = {{History-Guided Video Diffusion}},
  year = {2025},
  booktitle = {International Conference on Machine Learning},
  url = {https://arxiv.org/abs/2502.06764},
  eprint = {2502.06764},
  archivePrefix = {arXiv}
}

@inproceedings{Yin2025CausVid,
  author = {Yin, Tianwei and Zhang, Qiang and Zhang, Richard and Freeman, William T. and Durand, Fredo and Shechtman, Eli and Huang, Xun},
  title = {{From Slow Bidirectional to Fast Autoregressive Video Diffusion Models}},
  year = {2025},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://arxiv.org/abs/2412.07772},
  eprint = {2412.07772},
  archivePrefix = {arXiv},
  doi = {10.1109/cvpr52734.2025.02138}
}

@inproceedings{Huang2025SelfForcing,
  author = {Huang, Xun and Li, Zhengqi and He, Guande and Zhou, Mingyuan and Shechtman, Eli},
  title = {{Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion}},
  year = {2025},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://arxiv.org/abs/2506.08009},
  eprint = {2506.08009},
  archivePrefix = {arXiv}
}

@inproceedings{Yang2026LongLive,
  author = {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},
  title = {{LongLive: Real-time Interactive Long Video Generation}},
  year = {2026},
  booktitle = {International Conference on Learning Representations},
  url = {https://proceedings.iclr.cc/paper_files/paper/2026/hash/91a1610c6ed9e02d33f826b46f472b92-Abstract-Conference.html},
  eprint = {2509.22622},
  archivePrefix = {arXiv},
  volume = {2026},
  pages = {90037--90059}
}

@inproceedings{Henschel2025StreamingT2V,
  author = {Henschel, Roberto and Khachatryan, Levon and Poghosyan, Hayk and Hayrapetyan, Daniil and Tadevosyan, Vahram and Wang, Zhangyang and Navasardyan, Shant and Shi, Humphrey},
  title = {{StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text}},
  year = {2025},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  url = {https://openaccess.thecvf.com/content/CVPR2025/html/Henschel_StreamingT2V_Consistent_Dynamic_and_Extendable_Long_Video_Generation_from_Text_CVPR_2025_paper.html},
  eprint = {2403.14773},
  archivePrefix = {arXiv},
  pages = {2568--2577},
  doi = {10.1109/cvpr52734.2025.00245}
}

@inproceedings{Kim2024FIFODiffusion,
  author = {Kim, Jihwan and Kang, Junoh and Choi, Jinyoung and Han, Bohyung},
  title = {{FIFO-Diffusion: Generating Infinite Videos from Text without Training}},
  year = {2024},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://arxiv.org/abs/2405.11473},
  eprint = {2405.11473},
  archivePrefix = {arXiv}
}

@inproceedings{Qiu2024FreeNoise,
  author = {Qiu, Haonan and Xia, Menghan and Zhang, Yong and He, Yingqing and Wang, Xintao and Shan, Ying and Liu, Ziwei},
  title = {{FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling}},
  year = {2024},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2310.15169},
  eprint = {2310.15169},
  archivePrefix = {arXiv}
}

@inproceedings{Wu2023TuneAVideo,
  author = {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},
  title = {{Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation}},
  year = {2023},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  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},
  eprint = {2212.11565},
  archivePrefix = {arXiv},
  pages = {7623--7633},
  doi = {10.1109/iccv51070.2023.00701}
}

@inproceedings{Wang2023VideoComposer,
  author = {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},
  title = {{VideoComposer: Compositional Video Synthesis with Motion Controllability}},
  year = {2023},
  booktitle = {Advances in Neural Information Processing Systems},
  doi = {10.52202/075280-0334},
  url = {https://proceedings.neurips.cc/paper_files/paper/2023/hash/180f6184a3458fa19c28c5483bc61877-Abstract-Conference.html},
  eprint = {2306.02018},
  archivePrefix = {arXiv},
  volume = {36},
  pages = {7594--7611}
}

@inproceedings{Wu2024iVideoGPT,
  author = {Wu, Jialong and Yin, Shaofeng and Feng, Ningya and He, Xu and Li, Dong and Hao, Jianye and Long, Mingsheng},
  title = {{iVideoGPT: Interactive VideoGPTs are Scalable World Models}},
  year = {2024},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://arxiv.org/abs/2405.15223},
  eprint = {2405.15223},
  archivePrefix = {arXiv}
}

@inproceedings{Huang2026Vid2World,
  author = {Huang, Siqiao and Wu, Jialong and Zhou, Qixing and Miao, Shangchen and Long, Mingsheng},
  title = {{Vid2World: Crafting Video Diffusion Models to Interactive World Models}},
  year = {2026},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2505.14357},
  eprint = {2505.14357},
  archivePrefix = {arXiv}
}

@inproceedings{Yuan2026Lumos1,
  author = {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},
  title = {{Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective}},
  year = {2026},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/2507.08801},
  eprint = {2507.08801},
  archivePrefix = {arXiv}
}

@inproceedings{Yu2025GameFactory,
  author = {Yu, Jiwen and Qin, Yiran and Wang, Xintao and Wan, Pengfei and Zhang, Di and Liu, Xihui},
  title = {{GameFactory: Creating New Games with Generative Interactive Videos}},
  year = {2025},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  url = {https://arxiv.org/abs/2501.08325},
  eprint = {2501.08325},
  archivePrefix = {arXiv},
  doi = {10.1109/iccv51701.2025.01078}
}

@article{Xiang2024Pandora,
  author = {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},
  title = {{Pandora: Towards General World Model with Natural Language Actions and Video States}},
  year = {2024},
  journal = {arXiv preprint arXiv:2406.09455},
  url = {https://arxiv.org/abs/2406.09455},
  eprint = {2406.09455},
  archivePrefix = {arXiv}
}

@inproceedings{Hafner2019PlaNet,
  author = {Hafner, Danijar and Lillicrap, Timothy and Fischer, Ian and Villegas, Ruben and Ha, David and Lee, Honglak and Davidson, James},
  title = {{Learning Latent Dynamics for Planning from Pixels}},
  year = {2019},
  booktitle = {International Conference on Machine Learning},
  url = {https://arxiv.org/abs/1811.04551},
  eprint = {1811.04551},
  archivePrefix = {arXiv}
}

@inproceedings{Hafner2020Dreamer,
  author = {Hafner, Danijar and Lillicrap, Timothy and Ba, Jimmy and Norouzi, Mohammad},
  title = {{Dream to Control: Learning Behaviors by Latent Imagination}},
  year = {2020},
  booktitle = {International Conference on Learning Representations},
  url = {https://arxiv.org/abs/1912.01603},
  eprint = {1912.01603},
  archivePrefix = {arXiv}
}

@article{Hafner2025DreamerV3,
  author = {Hafner, Danijar and Pasukonis, Jurgis and Ba, Jimmy and Lillicrap, Timothy},
  title = {{Mastering diverse control tasks through world models}},
  year = {2025},
  journal = {Nature},
  doi = {10.1038/s41586-025-08744-2},
  url = {https://doi.org/10.1038/s41586-025-08744-2},
  eprint = {2301.04104},
  archivePrefix = {arXiv},
  volume = {640},
  pages = {647--653}
}

@article{Schrittwieser2020MuZero,
  author = {Schrittwieser, Julian and Antonoglou, Ioannis and Hubert, Thomas and Simonyan, Karen and Sifre, Laurent and Schmitt, Simon and Guez, Arthur and Lockhart, Edward and Hassabis, Demis and Graepel, Thore and Lillicrap, Timothy and Silver, David},
  title = {{Mastering Atari, Go, chess and shogi by planning with a learned model}},
  year = {2020},
  journal = {Nature},
  doi = {10.1038/s41586-020-03051-4},
  url = {https://doi.org/10.1038/s41586-020-03051-4},
  eprint = {1911.08265},
  archivePrefix = {arXiv},
  volume = {588},
  pages = {604--609}
}

@article{Assran2025VJEPA2,
  author = {Assran, Mahmoud and Bardes, Adrien and Fan, David and Garrido, Quentin and Howes, Russell and Komeili, Mojtaba and Muckley, Matthew and Rizvi, Ammar and Roberts, Claire and Sinha, Koustuv and Zholus, Artem and Arnaud, Sergio and Gejji, Abha and Martin, Ada and Hogan, Francois Robert and Dugas, Daniel and Bojanowski, Piotr and Khalidov, Vasil and Labatut, Patrick and Massa, Francisco and Szafraniec, Marc and Krishnakumar, Kapil and Li, Yong and Ma, Xiaodong and Chandar, Sarath and Meier, Franziska and LeCun, Yann and Rabbat, Michael and Ballas, Nicolas},
  title = {{V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning}},
  year = {2025},
  journal = {arXiv preprint arXiv:2506.09985},
  url = {https://arxiv.org/abs/2506.09985},
  eprint = {2506.09985},
  archivePrefix = {arXiv}
}

@inproceedings{Banerjee2025HOT3D,
  author = {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},
  title = {{HOT3D}: Hand and Object Tracking in {3D} from Egocentric Multi-View Videos},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2025},
  pages = {7061--7071},
  doi = {10.1109/CVPR52734.2025.00662},
  url = {https://openaccess.thecvf.com/content/CVPR2025/html/Banerjee_HOT3D_Hand_and_Object_Tracking_in_3D_from_Egocentric_Multi-View_CVPR_2025_paper.html}
}

% Targeted 2026 coverage additions, verified 23 October 2026.

@inproceedings{Ding2026FullPart,
  author = {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},
  title = {{FullPart: Generating each 3D Part at Full Resolution}},
  year = {2026},
  url = {https://proceedings.iclr.cc/paper_files/paper/2026/hash/4c2092ec0b1370cce3fb5965ab255fae-Abstract-Conference.html},
  booktitle = {International Conference on Learning Representations},
  eprint = {2510.26140},
  archivePrefix = {arXiv},
}

@inproceedings{Zhu2026CubePart,
  author = {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},
  title = {{CubePart: An Open-Vocabulary Part-Controllable 3D Generator}},
  year = {2026},
  url = {https://doi.org/10.1145/3799902.3811117},
  booktitle = {SIGGRAPH Conference Papers},
  eprint = {2605.28763},
  archivePrefix = {arXiv},
  doi = {10.1145/3799902.3811117},
}

@inproceedings{Xu2026MeshMosaic,
  author = {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},
  title = {{MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly}},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Xu_MeshMosaic_Scaling_Artist_Mesh_Generation_via_Local-to-Global_Assembly_CVPR_2026_paper.html},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  eprint = {2509.19995},
  archivePrefix = {arXiv},
  pages = {20003--20013},
}

@misc{Gu2026Seed3D2,
  author = {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},
  title = {{Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation}},
  year = {2026},
  url = {https://arxiv.org/abs/2605.13862},
  eprint = {2605.13862},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2605.13862},
}

@inproceedings{Gupta2026MaterialApprentice,
  author = {Gupta, Kunal and Joshi, Gaurav and Chen, Yen-Ru and Jain, Seemandhar and Mehta, Ishit and Chandraker, Manmohan},
  title = {{Reflecting Process Expertise in Procedural Material Generation}},
  booktitle = {Computer Vision -- ECCV 2026},
  series = {Lecture Notes in Computer Science},
  volume = {17046},
  pages = {318--336},
  publisher = {Springer},
  year = {2026},
  doi = {10.1007/978-3-032-37281-9_19},
  url = {https://link.springer.com/chapter/10.1007/978-3-032-37281-9_19}
}

@inproceedings{Xia2026SAGE,
  author = {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},
  title = {{SAGE: Scalable Agentic 3D Scene Generation for Embodied AI}},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Xia_SAGE_Scalable_Agentic_3D_Scene_Generation_for_Embodied_AI_CVPR_2026_paper.html},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  eprint = {2602.10116},
  archivePrefix = {arXiv},
  pages = {22358--22368},
}

@inproceedings{Ling2026IScene,
  author = {Ling, Lu and Ge, Yunhao and Sheng, Yichen and Bera, Aniket},
  title = {{I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners}},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Ling_I-Scene_3D_Instance_Models_are_Implicit_Generalizable_Spatial_Learners_CVPR_2026_paper.html},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  eprint = {2512.13683},
  archivePrefix = {arXiv},
  pages = {26974--26983},
}

@misc{Kim2026SceneFrom3D,
  author = {Kim, Geonung and Park, Jeongeun and Ryu, Nuri and Liu, Di and Cho, Sunghyun},
  title = {{SceneFrom3D: Geometry-Conditioned Outdoor 3D Scene Generation via View Scheduling with Object-Level Control}},
  year = {2026},
  url = {https://arxiv.org/abs/2607.04540},
  eprint = {2607.04540},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2607.04540},
}

@inproceedings{Ling2026Scenethesis,
  author = {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},
  title = {{Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation}},
  year = {2026},
  url = {https://proceedings.iclr.cc/paper_files/paper/2026/hash/dd172fa21119391253587a4310a1a426-Abstract-Conference.html},
  booktitle = {International Conference on Learning Representations},
  eprint = {2505.02836},
  archivePrefix = {arXiv},
}

@inproceedings{Lillemark2026FloWM,
  title = {{Flow Equivariant World Models: Structured Memory for Dynamic Environments}},
  author = {Lillemark, Hansen and Huang, Benhao and Zhan, Fangneng and Du, Yilun and Keller, T. Anderson},
  booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
  year = {2026},
  volume = {306},
  pages = {73968--74002},
  url = {https://proceedings.mlr.press/v306/lillemark26a.html},
  eprint = {2601.01075},
  archivePrefix = {arXiv}
}

@article{Duan2026LiveWorld,
  title = {{LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models}},
  author = {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},
  journal = {arXiv preprint arXiv:2603.07145},
  year = {2026},
  doi = {10.48550/arXiv.2603.07145},
  url = {https://arxiv.org/abs/2603.07145v2},
  eprint = {2603.07145},
  archivePrefix = {arXiv}
}

@article{Savva2026Solaris,
  title = {{Solaris: Building a Multiplayer Video World Model in Minecraft}},
  author = {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},
  journal = {arXiv preprint arXiv:2602.22208},
  year = {2026},
  doi = {10.48550/arXiv.2602.22208},
  url = {https://arxiv.org/abs/2602.22208v2},
  eprint = {2602.22208},
  archivePrefix = {arXiv}
}

@inproceedings{Wang2026AnchorWeave,
  title = {{AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories}},
  author = {Wang, Zun and Lin, Han and Yoon, Jaehong and Cho, Jaemin and Zhang, Yue and Bansal, Mohit},
  booktitle = {Computer Vision -- ECCV 2026},
  year = {2026},
  volume = {17051},
  pages = {203--224},
  doi = {10.1007/978-3-032-37356-4_12},
  url = {https://link.springer.com/chapter/10.1007/978-3-032-37356-4_12},
  eprint = {2602.14941},
  archivePrefix = {arXiv}
}

@article{Xiong2026ActWorld,
  title = {{ActWorld: From Explorable to Interactive World Model via Action-Aware Memory}},
  author = {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},
  journal = {arXiv preprint arXiv:2606.17730},
  year = {2026},
  doi = {10.48550/arXiv.2606.17730},
  url = {https://arxiv.org/abs/2606.17730v1},
  eprint = {2606.17730},
  archivePrefix = {arXiv}
}

@article{Huang2026ProgrammableWorld,
  title = {{Programmable World Model}},
  author = {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},
  journal = {arXiv preprint arXiv:2609.10540},
  year = {2026},
  doi = {10.48550/arXiv.2609.10540},
  url = {https://arxiv.org/abs/2609.10540v2},
  eprint = {2609.10540},
  archivePrefix = {arXiv}
}

@article{Wang2026WorldDirector,
  title = {{WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory}},
  author = {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},
  journal = {arXiv preprint arXiv:2607.02517},
  year = {2026},
  doi = {10.48550/arXiv.2607.02517},
  url = {https://arxiv.org/abs/2607.02517v1},
  eprint = {2607.02517},
  archivePrefix = {arXiv}
}

@article{Chen2026Full4D,
  title = {{Full-4D: Generating Full-Scope 4D Scenes from a Single-View Video}},
  author = {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},
  journal = {arXiv preprint arXiv:2605.25500},
  year = {2026},
  doi = {10.48550/arXiv.2605.25500},
  url = {https://arxiv.org/abs/2605.25500v1},
  eprint = {2605.25500},
  archivePrefix = {arXiv}
}

@misc{Jiang2026PartInteractor,
  author = {Jianan Jiang and Bin Li},
  title = {{PartInteractor: Intent-Driven Part-Aware 3D Authoring for Continuous Co-Creation in XR}},
  year = {2026},
  eprint = {2608.01335},
  archivePrefix = {arXiv},
  primaryClass = {cs.HC},
  doi = {10.48550/arXiv.2608.01335},
  url = {https://arxiv.org/abs/2608.01335v1},
  note = {Preprint v1, 2 August 2026; accepted to UIST 2026}
}

@misc{Ihara2026CinemaWorld,
  author = {Keiichi Ihara and DaeHo Lee and Manato Abe and Hye-Young Jo and Ryo Suzuki},
  title = {{CinemaWorld: Generative Augmented Reality with LLMs and 3D Scene Generation for Movie Augmentation}},
  year = {2026},
  eprint = {2603.08060},
  archivePrefix = {arXiv},
  primaryClass = {cs.HC},
  doi = {10.48550/arXiv.2603.08060},
  url = {https://arxiv.org/abs/2603.08060v1},
  note = {Preprint v1, 9 March 2026; accepted to UIST 2026}
}

@article{Yuan2026ImmerseGen,
  author = {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},
  title = {{ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies}},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  year = {2026},
  volume = {32},
  number = {5},
  pages = {3530--3540},
  doi = {10.1109/TVCG.2026.3679097},
  url = {https://immersegen.github.io/},
  eprint = {2506.14315},
  archivePrefix = {arXiv}
}

@inproceedings{Srinidhi2026GenAssist,
  author = {Sruti Srinidhi and Akul Singh and Edward Lu and Anthony Rowe},
  title = {{GenAssist: Interactive Prompt-Driven XR Program Generation}},
  booktitle = {2026 IEEE Conference on Virtual Reality and 3D User Interfaces (VR)},
  year = {2026},
  pages = {615--625},
  publisher = {IEEE},
  doi = {10.1109/VR67842.2026.00081},
  url = {https://www.srutisrinidhi.com/GenAssist/}
}

@misc{Mei2026ShadAR,
  author = {Yanni Mei and Samuel Hartenstein and Jonas Wombacher and Florian Mueller and Jan Gugenheimer},
  title = {{ShadAR: Real-time Prompting On-demand Visual Augmentation in Augmented Reality}},
  year = {2026},
  eprint = {2610.19998},
  archivePrefix = {arXiv},
  primaryClass = {cs.HC},
  doi = {10.48550/arXiv.2610.19998},
  url = {https://arxiv.org/abs/2610.19998v1},
  note = {Preprint v1, 14 October 2026; accepted to UIST 2026}
}
