Mingde Yao (姚明德)
Agentic AI · Deep Generative Models · Computational Photography

Google Scholar  /  Github  /  Zhihu

 

Postdoctoral Researcher, MMLab@CUHK (Multimedia Laboratory, The Chinese University of Hong Kong)
Email : mingdeyao (at) foxmail.com

About Me

Currently, I am a Postdoctoral Researcher at Multimedia Laboratory (MMLab), The Chinese University of Hong Kong (CUHK), advised by Prof. Tianfan Xue, Prof. Jinwei Gu and Prof. Hongsheng Li. Before that, I obtained my Ph.D. degree from University of Science and Technology of China (USTC) in 2023, advised by Prof. Zhiwei Xiong. I obtained my B. Eng. degree in the Department of Automation (Lang Shijun Honors Class) from Northeastern University, China, in 2018.

My research interests broadly lie in the areas of Agentic AI, deep generative models, computational photography, and general fields of computer vision and machine learning.

I am always open to collaborations and discussions! If you are interested in my research or have any ideas to share, feel free to reach out.

Updates

Selected Publications [ Full List ]

PolarFree: Polarization-based Reflection-Free Imaging
Mingde Yao, Menglu Wang, King-Man Tam, Lingen Li, Tianfan Xue, and Jinwei Gu.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
[ PDF ] [ Project page ] [ Code ] [ Dataset ]
Uni-ISP: Unifying the Learning of ISPs from Multiple Cameras
Lingen Li, Mingde Yao, Xingyu Meng, Muquan Yu, Tianfan Xue, and Jinwei Gu.
arXiv Preprint, 2024
[ Project page ] [ PDF ] [ Video ] [ Code ] [ FiveCam Dataset ]
Continuous Spatial-Spectral Reconstruction via Implicit Neural Representation
Ruikang Xu, Mingde Yao,Chang Chen, Lizhi Wang, and Zhiwei Xiong.
ECCV Mobile Intelligent Photography & Imaging Workshop (ECCVW) , 2022
[Best Paper Honorable Mention]
International Journal of Computer Vision (IJCV), 2024
[ PDF (Conference Version) ] [ PDF (Journal Version) ] [ Code ]
Neural Degradation Representation Learning for All-In-One Image Restoration
Mingde Yao, Ruikang Xu, Yuanshen Guan, Jie Huang, and Zhiwei Xiong.
Transactions on Image Processing (T-IP), 2024
[ PDF ] [ Code ]
Generalized Lightness Adaptation with Channel Selective Normalization
Mingde Yao*, Jie Huang*, Xin Jin, Ruikang Xu, Shenglong Zhou, Man Zhou, and Zhiwei Xiong.
IEEE International Conference on Computer Vision (ICCV), 2023
[ PDF ] [ Code ]
Zero-Shot Dual-Lens Super-Resolution
Ruikang Xu*, Mingde Yao*, and Zhiwei Xiong.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2023
[ PDF ] [ Code ] [ Slide ] [ Video ]
Ingredient-oriented Multi-Degradation Learning for Image Restoration
Jinghao Zhang, Jie Huang, Mingde Yao, Zizheng Yang, Hu Yu, Man Zhou, and Feng Zhao.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2023
[ PDF ] [ Bibtex ]
      @inproceedings{zhang2023ingredient,
      title={Ingredient-Oriented Multi-Degradation Learning for Image Restoration},
      author={Zhang, Jinghao and Huang, Jie and Yao, Mingde and Yang, Zizheng and Yu, Hu and Zhou, Man and Zhao, Feng},
      booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
      pages={5825--5835},
      year={2023}
      }

Bidirectional Translation between HD-SDR and UHD-HDR Videos
Mingde Yao, Dongliang He, Xin Li, Zhihong Pan, and Zhiwei Xiong.
Transactions on Multimedia (T-MM) , 2023
[ PDF ] [ Code ]
Towards Interactive Self-Supervised Denoising
Mingde Yao, Dongliang He, Xin Li, Fu Li, and Zhiwei Xiong.
IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT) , 2023
[ PDF ] [ Code ] [ Bibtex ]
      @article{yao2023towards,
      title={Towards interactive self-supervised denoising},
      author={Yao, Mingde and He, Dongliang and Li, Xin and Li, Fu and Xiong, Zhiwei},
      journal={IEEE Transactions on Circuits and Systems for Video Technology},
      year={2023},
      publisher={IEEE}
      }

Spectral-depth imaging with deep learning based reconstruction
Mingde Yao, Zhiwei Xiong, Lizhi Wang, Dong Liu, and Xuejin Chen.
Optics Express (OE) , 2019
[ PDF ]

Awards

  • Winner of Bokeh Effect Synthesis in ICCV AIM Challenge, 2019
  • Runner-Up of Burst Super-Resolution in CVPR NTIRE Challenge, 2022
  • Second runner-up of Atmospheric Turbulence Mitigation in CVPR UG+ Challenge, 2022

Academic Activities

Reviewer

  • T-PAMI, IJCV, T-NNLS, T-IP, T-MM, T-CSVT, CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, AISTATS, AAAI, ACMMM, IJCAI, ICME, etc.

    • Guest Editor

  • Special Issue on "Foundation Models and Prompting for Visual Tasks in Harsh Conditions" in Pattern Recognition.

    • Last Updated in March, 2026

    Published with GitHub Pages