Guoxi Huang (Edward)

I am a Postdoctoral Research Associate at the University of Bristol, advised by Prof. Nantheera Anantrasirichai (Pui). I am a member of the Visual Information Laboratory and the Bristol Vision Institute, which are both led by Prof. David Bull. Prior to this, I was a Senior Research Engineer at Baidu Inc. My research focuses on image generation, low-level vision, image/video understanding and other computer vision topics.

Google Scholar / LinkedIn

If you are interested in collaborating, please contact me via email at guoxi.huang@bristol.ac.uk

Publication (* = Equal Contribution, † = Corresponding Author)

	Bayesian Neural Networks for One-to-Many Mapping in Image Enhancement Guoxi Huang , Qirui Yang, Zipeng Qi, RuiRui Lin, David Bull, Nantheera Anantrasirichaii Association for the Advancement of Artificial Intelligence (AAAI), 2025 paper / project / bibtex An image enhancement model that can generate multiple enhanced images using Bayesian Neural Networks.
	RUSplatting: Robust 3D Gaussian Splatting for Sparse-View Underwater Scene Reconstruction Zhuodong Jiang, Haoran Wang, Guoxi Huang, Brett Seymour, Nantheera Anantrasirichai British Machine Vision Conference (BMVC), 2025 paper / project / bibtex A 3DGS for underwater scence rencostrction
	Layered Rendering Diffusion Model for Controllable Zero-Shot Image Synthesis Zipeng Qi, Guoxi Huang†*, Chenyang Liu, Fei Ye European Conference on Computer Vision (ECCV)*, 2024 paper / project / bibtex A novel image generation framework capable of producing images from specified layouts and shapes.
	BVI-RLV: A Fully Registered Dataset and Benchmarks for Low-Light Video Enhancement Ruirui Lin, Guoxi Huang† , Joanne Lin, Qi Sun, Alexandra Malyugina, David Bull, Nantheera Anantrasirichai† arxiv, 2024 paper / bibtex A fully registered low-light video dataset.
	Masked Image Residual Learning for Scaling Deeper Vision Transformers Guoxi Huang, Hongtao Fu, Adrian G Bors Neural Information Processing Systems (NeurIPS), 2023 paper / project / bibtex A novel masked image modeling framework for pre-training vision transformers.
	BQN: Busy-Quiet net enabled by motion band-pass module for action recognition Guoxi Huang, Adrian G Bors IEEE Transactions on Image Processing (TIP), 2022 paper / project / bibtex An efficient plug-and-play action recognition approach.

Guoxi Huang (Edward)

Publication (* = Equal Contribution, † = Corresponding Author)

Bayesian Neural Networks for One-to-Many Mapping in Image Enhancement

RUSplatting: Robust 3D Gaussian Splatting for Sparse-View Underwater Scene Reconstruction

Layered Rendering Diffusion Model for Controllable Zero-Shot Image Synthesis

BVI-RLV: A Fully Registered Dataset and Benchmarks for Low-Light Video Enhancement

Masked Image Residual Learning for Scaling Deeper Vision Transformers

BQN: Busy-Quiet net enabled by motion band-pass module for action recognition