Update: I am currently looking for talented students to work on innovative computer vision, computer graphics, medical imaging, and deep learning at HKUST (GZ). PhD/RA/Postdoc positions are available. The salaries will be highly competitive. Please drop me an email (with a title 'PHD/RA/Postdoc application') if you are interested. As a new campus of HKUST, HKUST (GZ) focuses on the interdisciplinary research.

Short Bio.

I am an assistant professor at ROAS Thrust, HKUST(GZ), and also an affiliated assistant professor at ECE, HKUST. Before that, I was a Postdoctoral researcher at DAMTP, University of Cambridge, working with Prof. Carola-Bibiane Schönlieb. My Ph.D. was obtained at the Department of Computer Science and Engineering, the Chinese University of Hong Kong under the supervision of Prof. Pheng-Ann Heng and Prof. Chi-Wing Fu, Philip in 2017. I have been serving as the PG coordinator of the ROAS Thrust since 2023. My research interests include computer vision, image restoration, image generation, medical AI, and deep learning. The main research goal is to answer the question of how to develop intelligent image perception methods for extracting useful information from visual content that is prevalent in live sources. These techniques benefit robotics, autonomous driving, healthcare, and so on. By now, our research works have been published in top-tier journals and conferences, e.g., IEEE TPAMI/IJCV/NeurIPS/CVPR/ICCV/ECCV, IEEE TIP/TNNLS/TMM/TCSVT/TVCG, AAAI/IJCAI/ACM-MM, and MICCAI/IEEE TMI/Medical Image Analysis/IEEE TBME. I have been invited as a Senior PC of AAAI 2026, IJCAI 2026 & 2025,  an Area Chair of MICCAI 2025 & 2024 & 2023, CVPR 2026 & 2025, ICLR 2026 & 2025, ECCV 2024, ACM Multimedia 2025 & 2022 & 2021, a program chair of ACM SIGGRAPH VRCAI 2025 & 2024 & 2022, and IEEE CW 2025,  and an organization chair of CGI 2025 & 2023, associate editor of The Visual Computer, and so on. He is an IEEE Senior Member.

Selected publications 

Summary: 39x CVPR/ICCV/ECCV(6), 9x NeurIPS/ICLR, 3x IEEE TPAMI, 4x IJCV, 

51. LucidFlux: Caption-Free Universal Image Restoration via a Large-Scale Diffusion Transformer

 Song Fei, Tian Ye, Lujia Wang, and Lei Zhu*,

To appear in ICLR, 2026.

50. PosterCraft:Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

 Sixiang Chen, Jianyu Lai, Jialin Gao, Tian Ye, Hengyu Shi, Haoyu Chen, Shitong Shao, Yunlong Lin, 

Song Fei, Zhaohu Xing, Yeying Jin, Junfeng Luo, Xiaoming Wei, and Lei Zhu*,

To appear in ICLR, 2026.

49. VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation, 

Sicheng Yang, Zhaohu Xing, and Lei Zhu*,

In NeurIPS, 2025.

48. Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis, 

Jingjing Ren, Wenbo Li, Zhongdao Wang, Haoze Sun, Bangzhen Liu, Haoyu Chen, Jiaqi Xu, Aoxue Li, Shifeng Zhang, Bin Shao, Yong Guo, and Lei Zhu*,

In IEEE/CVF ICCV, pp. 18155-18165, 2025.

47. GenHaze: Pioneering Controllable One-Step Realistic Haze Generation for Real-World Dehazing, 

Sixiang Chen, Tian Ye, Yunlong Lin, Yeying Jin, Yijun Yang, Haoyu Chen, Jianyu Lai, Song Fei, Zhaohu Xing, Fugee Tsung, and Lei Zhu*,

In IEEE/CVF ICCV, pp. 9194-9205, 2025.

46. Medical World Model, 

Yijun Yang, Zhao-Yang Wang, Qiuping Liu, Shu Wen Sun, Kang Wang, Rama Chellappa, Zongwei Zhou, Alan Yuille, Lei Zhu*, Yu-Dong Zhang, Jieneng Chen*

In IEEE/CVF ICCV, pp. 8319-8329, 2025.

45. Toward Fair and Accurate Cross-Domain Medical Image Segmentation: A VLM-Driven Active Domain Adaptation Paradigm, 

Hongqiu Wang, Wu Chen, Xiangde Luo, Zhaohu Xing, Lihao Liu, Jing Qin, Shaozhi Wu, and Lei Zhu*,

In IEEE/CVF ICCV, pp. 24102-24112, 2025.

44. GlassWizard: Harvesting Diffusion Priors for Glass Surface Detection, 

Wenxue Li, Tian Ye, Xinyu Xiong, Jinbin Bai, Feilong Tang, Wenxuan Song, Zhaohu Xing, Lie Ju, Guanbin Li, and Lei Zhu*,

In IEEE/CVF ICCV, pp. 17848-17858, 2025.

43.SnowMaster: Comprehensive Real-world Image Desnowing via MLLM with Multi-Model Feedback Optimization,

Jianyu Lai, Sixiang Chen, Yunlong Lin, Tian Ye, Yun Liu, Song Fei, Zhaohu Xing, HongtaoWu, Weiming Wang, and Lei Zhu*,

In IEEE/CVF CVPR, pp. 4302-4312, 2025.  

42. Detect Any Mirrors: Boosting Learning Reliability on Large-Scale Unlabeled Data with an Iterative Data Engine

Zhaohu Xing, Lihao Liu, Yijun Yang, Hongqiu Wang, Tian Ye, Sixiang Chen, Wenxue Li, Guang Liu, and Lei Zhu*,

In IEEE/CVF CVPR, pp. 25476-25486,  2025.  

41. A Simple Data Augmentation for Feature Distribution Skewed Federated Learning,

Yunlu Yan, Huazhu Fu, Yuexiang Li, Jinheng Xie, Jun Ma, Guang Yang, and Lei Zhu*,

In IEEE/CVF CVPR, pp. 25749-25758, 2025.  

40. POSTA: A Go-to Framework for Customized Artistic Poster Generation,

Haoyu Chen, Xiaojie Xu, Wenbo Li, Jingjing Ren, Tian Ye, Songhua Liu, Ying-Cong Chen, Lei Zhu*, and Xinchao Wang

In IEEE/CVF CVPR, pp. 28694-28704, 2025.  

39. RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images,

Junjin Xiao, Qing Zhang, Yongwei Nie, Lei Zhu, and Wei-Shi Zheng,

In IEEE/CVF CVPR, pp.5980-5990, 2025.  

38. Federated Residual Low-Rank Adaptation of Large Language Models,

Yunlu Yan, Chun-Mei Feng, Wangmeng Zu, Rick Siow Mong Goh, Yong Liu, and Lei Zhu*,

In ICLR, 2025.  

37. On the Importance of Language-driven Representation Learning for Heterogeneous Federated Learning,

Yunlu Yan, Chun-Mei Feng, Wangmeng Zuo, Salman Khan, Yong Liu, and Lei Zhu*, 

In ICLR, 2025.  

36. Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Jinbin Bai, Tian Ye, Wei Chow, Enxin Song, Qing-Guo Chen, Xiangtai Li, Zhen Dong, Lei Zhu*, and Shuicheng Yan*,

In ICLR, 2025.  

35. UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks

Jingjing Ren*, Wenbo Li*, Haoyu Chen, Renjing Pei, Bin Shao, Yong Guo, Long Peng, and Lei Zhu*.

In NeurIPS, 2024.

34. RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models

Haoyu Chen, Wenbo Li, Jinjin Gu, Jingjing Ren, Sixiang Chen, Tian Ye, Renjing Pei, Kaiwen Zhou, Fenglong Song, and Lei Zhu*.

In NeurIPS, 2024.

33. Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint

Sixiang Chen, Tian Ye, Kai Zhang, Zhaohu Xing, Yunlong Lin, and Lei Zhu*,

In ECCV, pp. 95-115, 2024. 

32. Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization

Hongtao Wu, Yijun Yang, Angelica Aviles-Rivero, Jingjing Ren, Sixiang Chen, Haoyu Chen, and Lei Zhu*,

In ECCV, pp 70–89, 2024. 

31. Two-Stage Video Shadow Detection via Temporal-Spatial Adaptation

Xin Duan, Yu Cao, Lei Zhu, Gang Fu, Xin Wang, Renjie ZHANG, and Ping Li

In ECCV,  pp 196–214, 2024. 

30. OpenIn-s3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation

Zhening Huang, Xiaoyang Wu, Xi Chen, Hengshuang Zhao, Lei Zhu, and Joan Lasenby,

In ECCV, pp 169–185, 2024. 

29. Triplane-Smoothed Video Dehazing with CLIP-Enhanced Generalization

Jingjing Ren, Tian Ye, Haoyu Chen, Hongtao Wu, and Lei Zhu*.

International Journal of Computer Vision (IJCV), Vol.133, pp. 475–488, 2025.

28. Learning Diffusion Texture Priors for Image Restoration

Tian Ye, Sixiang Chen, Wenhan Chai, Zhaohu Xing, Jing Qin, Ge Lin, and Lei Zhu*,

In IEEE/CVF CVPR, pp. 2524-2534, 2024. 

27. Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal

Yijun Yang, Hongtao Wu, Angelica Aviles-Rivero, Yulun Zhang, Jing Qin, and Lei Zhu*,

In IEEE/CVF CVPR, pp. 25606-25616,  2024. 

26. Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning

Haoyu Chen, Wenbo Li, Jinjin Gu, Jingjing Ren, Haoze Sun, Xueyi Zou, Youliang Yan, Zhensong Zhang, and Lei Zhu*,

In IEEE/CVF CVPR, pp. 25857-25867, 2024. 

25. ViDSOD-100: A New Dataset and A Baseline Model for RGB-D Video Salient Object Detection, 

Junhao Lin, Lei Zhu*, Jiaxing Shen, Huazhu Fu, Qing Zhang, and Liansheng Wang,

International Journal of Computer Vision (IJCV), Vol.132, pp. 5173–5191, 2024. 

24. Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation,

Yijun Yang, Angelica Aviles-Rivero, Ye Liu, Huazhu Fu, Weiming Wang, and Lei Zhu*, 

In IEEE/CVF ICCV, pp. 13200-13210, 2023. [Project & Code]

23. Snow Removal in Video: A New Dataset and A Novel Method, 

Haoyu Chen, Jingjing Ren, Jinjin Gu, Hongtao Wu, Xuequan Lu, Haoming Cai, and Lei Zhu*, 

In IEEE/CVF ICCV, pp. 13211-13222 , 2023. [Project & Code]

22. Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks, 

Sixiang Chen, Tian Ye, Jinbin Bai, Erkang Chen, Shi Jun, and Lei Zhu*, 

In IEEE/CVF ICCV, pp. 13106-13117,  2023. [Project & Code]

21. Towards High-quality Specular Highlight Removal by Leveraging Large-scale Synthetic Data

Gang Fu, Qing Zhang, Lei Zhu, Chunxia Xiao, and Ping Li, 

In IEEE/CVF ICCV, pp. 12857-12865, 2023. 

20. Towards High-Resolution Specular Highlight Detection

Gang Fu, Qing Zhang, Lei Zhu, Qifeng Lin, Yihao Wang, Siyuan Fan, and Chunxia Xiao

International Journal of Computer Vision (IJCV), 132, pp. 95–117,  2023. 

19. MNGNAS: Distilling Adaptive Combination of Multiple Searched Networks for One-Shot Neural Architecture Search 

Zhihua Chen, Guhao Qiu, Ping Li, Lei Zhu, Xiaokang Yang, and Bin Sheng

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Volume 45, Issue 11, pp. 13489-13508, 2023.

18. Masked Image Pre-training for Generalizable Image Denoising, 

Haoyu Chen, Jinjin Gu, Yihao Liu, Salma Abdel Magid, Chao Dong, Qiong Wang, Hanspeter Pfister, and Lei Zhu*, 

In IEEE/CVF CVPR, pp. 1692-1703, 2023. [GitHub]

17. Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior, 

Jiaqi Xu, Xiaowei Hu*, Lei Zhu*, Qi Dou, Jifeng Dai, Yu Qiao, and Pheng-Ann Heng, 

In IEEE/CVF CVPR, pp. 18053-18062, 2023. [GitHub]

16. SCOTCH and SODA: A Transformer Video Shadow Detection Framework,

Lihao Liu, Jean Prost, Lei Zhu, Nicolas Papadakis, Pietro Lio, Carola-Bibiane Schönlieb, and Angelica I Aviles-Rivero, 

In IEEE/CVF CVPR, pp. 10449-10458, 2023. [GitHub]

15. Learning to Remove Shadows from a Single Image

Hao Jiang, Qing Zhang, Yongwei Nie, Lei Zhu, and Wei-Shi Zheng

International Journal of Computer Vision (IJCV), 131, pp. 2471–2488, 2023.

14. Rethinking Video Rain Streak Removal: A New Synthesis Model and A Deraining Network with Video Rain Prior

Shuai Wang, Lei Zhu*, Huazhu Fu, Jing Qin, Carola-Bibiane Schönlieb, Wei Feng, and Song Wang

ECCV, pp. 565-582,  2022. [GitHub]

13. RSCFed: Random Sampling Consensus Federated Semi-supervised Learning

Xiaoxiao Liang, Yiqun Lin, Huazhu Fu, Lei Zhu, Xiaomeng Li

In IEEE/CVF CVPR, pp. 10154-10163,  2022. [GitHub]

12. VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection

Yujun Zhang^, Lei Zhu^, Wei Feng, Huazhu Fu, Mingqian Wang, Qingxia Li, Cheng Li, and Song Wang  (^ joint 1st authors)

In IEEE/CVF ICCV, pp. 15681-15690, 2021. [GitHub] [Dataset]

11. Triple-cooperative Video Shadow Detection

Zhihao Chen, Liang Wan, Lei Zhu*, Jia Shen, Huazhu Fu, Wennan Liu, and Jing Qin

In IEEE/CVF CVPR, pp. 2715–2724, 2021. [GitHub] [Dataset]

10. A Multi-Task Network for Joint Specular Highlight Detection and Removal 

Gang Fu, Qing Zhang, Lei Zhu, Ping Li, and Chunxia Xiao

In IEEE/CVF CVPR, pp. 7752–7761, 2021. [GitHub]

9. Unsupervised Intrinsic Image Decomposition Using Internal Self-similarity Cues

Qing Zhang, Jin Zhou, Lei Zhu, Wei Sun, Chunxia Xiao, and Wei-Shi Zheng

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 44, No. 12, pp. 9669–9686, 2022. 

8. A Multi-task Mean Teacher for Semi-supervised Shadow Detection 

Zhihao Chen^, Lei Zhu^, Liang Wan, Song Wang, Wei Feng, and Pheng-Ann Heng (^ joint 1st authors)

In IEEE/CVF CVPR, pp. 5611–5620, 2020. [GitHub]

7. Direction-aware Spatial Context Features for Shadow Detection and Removal

Xiaowei Hu, Chi-Wing Fu, Lei Zhu*, Jing Qin, and Pheng-Ann Heng

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 42, No. 11, pp. 2795–2808, 2020.

6. Deep Multi-Model Fusion for Single-Image Dehazing 

Zijun Deng^, Lei Zhu^, Xiaowei Hu, Chi-Wing Fu, Xuemiao Xu, Qing Zhang, Jing Qin, and Pheng-Ann Heng (^ joint 1st authors)

In IEEE/CVF ICCV, pp. 2453–2462, 2019.  [GitHub] [Code]

5. Depth-attentional Features for Single-image Rain Removal

Xiaowei Hu, Chi-Wing Fu, Lei Zhu*, and Pheng-Ann Heng

In IEEE/CVF CVPR,  pp. 8022–8031, 2019. 

4. Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection 

Lei Zhu, Zijun Deng, Xiaowei Hu, Chi-Wing Fu, Xuemiao Xu, Jing Qin, and Pheng-Ann Heng

ECCV, pp. 121–136, 2018.  [Github]    [Paper]   

3. Direction-aware Spatial Context Features for Shadow Detection 

Xiaowei Hu^, Lei Zhu^, Chi-Wing Fu, Jing Qin, and Pheng-Ann Heng (^ joint 1st authors)

In IEEE/CVF CVPR, pp. 7454–7462, 2018. [Github]  

2. Joint Bi-layer Optimization for Single-image Rain Streak Removal 

Lei Zhu, Chi-Wing Fu, Dani Lischinski, and Pheng-Ann Heng

In IEEE ICCV, pp. 2526–2534, 2017. 

1. A Non-Local Low-Rank Framework for Ultrasound Speckle Reduction 

Lei Zhu, Chi-Wing Fu, Michael S. Brown, and Pheng-Ann Heng

In IEEE CVPR, pp. 5650–5658, 2017. [Homepage]   

Copyright©2026 Henry