Hai Jiang (江海)

Second-year Ph.D. Student
Sichuan University, Chengdu, China
Email: jianghai@stu.scu.edu.cn
[GitHub] [Google Scholar] [CV]


Biography

I am currently a Ph.D. student in the School of Aeronautics and Astronautics, Sichuan University (SCU), supervised by Prof. Songchen Han. I obtained my B.E. and M.S. degrees from Sichuan University in 2020 and 2023, respectively.

From Jan. 2022 to the present, I have been working as a research intern at Megvii Technology (Megvii Research Chengdu), supervised by Prof. Shuaicheng Liu, Dr. Yuhang Lu, Dr. Ao Luo, and Haipeng Li.

My research interests include image restoration and image alignment, especially low-light image enhancement and homography estimation.

News

Selected Publications

  • ISPDiffuser: Learning RAW-to-sRGB Mappings with Texture-Aware Diffusion Models and Histogram-Guided Color Consistency
    YangRen*, Hai Jiang*, Menglong Yang, Wei Li, Shuaicheng Liu 
    Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI), 2025. [PDF] [Code]

  • LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models
    Hai Jiang, Ao Luo, Xiaohong Liu, Songchen Han, Shuaicheng Liu 
    European Conference on Computer Vision (ECCV), 2024. [PDF] [Code]

  • DMHomo: Learning Homography with Diffusion Models
    Haipeng Li, Hai Jiang, Ao Luo, Ping Tan, Haoqiang Fan, Bing Zeng, Shuaicheng Liu 
    ACM Transactions on Graphics (ToG, Presented at SIGGRAPH), 2024. [PDF] [Code]

  • Revisiting Coarse-to-fine Strategy for Low-Light Image Enhancement with Deep Decomposition Guided Training
    Hai Jiang, Yang Ren, Songchen Han 
    Computer Vision and Image Understanding (CVIU), 2024. [PDF] [Code]

  • Low-Light Image Enhancement with Wavelet-based Diffusion Models
    Hai Jiang, Ao Luo, Songchen Han, Haoqiang Fan, Shuaicheng Liu 
    ACM Transactions on Graphics (ToG, Proceedings of SIGGRAPH Asia), 2023. [PDF] [Code]

  • Supervised Homography Learning with Realistic Dataset Generation
    Hai Jiang*, Haipeng Li*, Songchen Han, Haoqiang Fan, Bing Zeng, Shuaicheng Liu 
    International Conference on Computer Vision (ICCV), 2023. [PDF] [Code]

  • Semi-supervised Deep Large-Baseline Homography Estimation with Progressive Equivalence Constraint
    Hai Jiang*, Haipeng Li*, Yuhang Lu, Songchen Han, Shuaicheng Liu 
    Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023. [PDF] [Code]

  • Unsupervised Global and Local Homography Estimation with Motion Basis Learning
    Shuaicheng Liu, Yuhang Lu, Hai Jiang, Nianjin Ye, Chuang Wang, Bing Zeng 
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023. [PDF] [Code]

  • R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network
    Hai Jiang, Xuan Zhu, Yang Ren, Yutong Hao, Fengzhu Zou, Lin Fang, Songchen Han 
    Journal of Visual Communication and Image Representation (JVCIR, Best Paper Runner-Up, ESI Highly Cited Paper), 2023. [PDF] [Code]

Awards

  • National Scholarship. Nov. 2024.
  • Outstanding Master's Thesis of Sichuan University. Jun. 2023.
  • First Prize of China Aerospace Foundation-Romax Technology Aerospace Scholarship. Oct. 2022.
  • Third Prize of Undergraduate Graduation Design (Thesis) of Sichuan University. Jun. 2020.

Academic Services

  • Journal reviewer:

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), International Journal of Computer Vision (IJCV), IEEE Transactions on Image Processing (TIP), IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), IEEE Signal Processing Letters (SPL), Computer Vision and Image Understanding (CVIU), Computers & Graphics (CG)


    • Conference Reviewer:

  • ACM SIGGRAPH Annual Conference (SIGGRAPH), AAAI Conference on Artificial Intelligence (AAAI), ACM International Conference on Multimedia (ACM MM), IEEE Conference on Computer Vision and Pattern Recognition (CVPR), European Conference on Computer Vision (ECCV), IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE International Conference on Multimedia and Expo (ICME)