prof_pic.jpg

Jinxiu (Sherry) Liang

I am a researcher at the National Institute of Informatics (NII) in Tokyo, Japan, where I work with Prof. Imari Sato on physics-based vision for fast and faint scenes.

Before joining NII, I was a postdoctoral fellow with Prof. Boxin Shi at the National Engineering Research Center of Visual Technology, Peking University, working on low-light high-speed photography with neuromorphic cameras. I received my Ph.D. and B.Eng. from South China University of Technology, advised by Prof. Yong Xu, and worked closely with Prof. Hui Ji and Prof. Yuhui Quan on optimization and image priors for inverse problems in low light.

Email / Google Scholar / researchmap / DBLP / ORCID / GitHub / LinkedIn

Research

Information is the resolution of uncertainty. — after Claude Shannon

Uncertainty has two resolvers: measurement and knowledge. A frame mostly re-measures what the previous frame established or knowledge predicts; the new information lives in change. I build imaging systems that sample the world on its own clock and let physics and generative priors supply the predictable rest, measuring fast, faint dynamics with a fraction of the light and data.

My research interests include:

  • Neuromorphic imaging: asynchronous detectors (e.g., event cameras) as continuous-time instruments, and optical coding that writes physical quantities into detection timing, reconstructing the field between and beyond frames.
  • Physics-guided generative priors: training-free reconstruction where paired data cannot exist at scale, from unconventional sensors to sparse measurements.
  • Low-light and high-speed imaging: recovering more from fewer photons and shorter acquisitions, from everyday scenes to scientific measurement.

Papers (Selected | Full List)

Note: # equal contribution (co-first author); * (co-)corresponding author; † co-mentored student.

  1. EventUPS: Uncalibrated Photometric Stereo Using an Event Camera
    EventUPS: Uncalibrated Photometric Stereo Using an Event Camera
    Jinxiu Liang#, Bohan Yu#, Siqi Yang, Haotian Zhuang, Jieji Ren, Peiqi Duan, and Boxin Shi
    IEEE International Conference on Computer Vision (ICCV), 2025 (Highlight, top 3% of 11,239 submissions)
    Also presented at ICCP 2026.
    pdf /video /conference page / poster
    Lighting written into time, normals read from events: surpassing frame-based accuracy at 5% of the bandwidth.
  2. SpikeDiff: Zero-shot High-Quality Video Reconstruction from Chromatic Spike Camera and Sub-millisecond Spike Streams
    SpikeDiff: Zero-shot High-Quality Video Reconstruction from Chromatic Spike Camera and Sub-millisecond Spike Streams
    Siqi Yang†, Jinxiu Liang*, Zhaojun Huang, Yeliduosi Xiaokaiti, Yakun Chang, Zhaofei Yu, and Boxin Shi*
    IEEE International Conference on Computer Vision (ICCV), 2025
    pdf /conference page / poster
    Physics-guided diffusion turns sub-millisecond spike streams into color video, zero-shot.
  3. Coherent Event Guided Low-Light Video Enhancement
    Coherent Event Guided Low-Light Video Enhancement
    Jinxiu Liang, Yixin Yang, Boyu Li, Peiqi Duan, Yong Xu, and Boxin Shi
    IEEE International Conference on Computer Vision (ICCV), 2023
    pdf /code /project page /video / poster
    Fast and faint at once: events keep low-light video sharp and temporally coherent.
  4. EventPS: Real-Time Photometric Stereo Using an Event Camera
    EventPS: Real-Time Photometric Stereo Using an Event Camera
    Bohan Yu†, Jieji Ren, Jin Han, Feishi Wang, Jinxiu Liang, and Boxin Shi
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024 (Best Paper Runners-Up, top 4 of 11,532 submissions)
    pdf /code /project page /video /conference page / poster
    Surface normals in real time, from an event camera watching changing light.
  5. Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models
    Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models
    Yan Huang, Xiaoshan Liao†, Jinxiu Liang*, Yuhui Quan, Boxin Shi, and Yong Xu
    AAAI Conference on Artificial Intelligence (AAAI), 2025
    pdf /code
    Pre-trained latent diffusion as the prior: low-light enhancement with zero training pairs.
  6. Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain
    Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain
    Hanyue Lou#†, Jinxiu Liang#, Minggui Teng, Bin Fan, Yong Xu, and Boxin Shi
    Advances in Neural Information Processing Systems (NeurIPS), 2024
    pdf /code /conference page / poster /slides
    Visual prompting lets image-domain foundation models read event streams, no event training.
  7. Self-Supervised Low-Light Image Enhancement Using Discrepant Untrained Network Priors
    Self-Supervised Low-Light Image Enhancement Using Discrepant Untrained Network Priors
    Jinxiu Liang, Yong Xu, Yuhui Quan, Boxin Shi, and Hui Ji
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022
    pdf /code
    Enhancement learned from nothing but the input image, via discrepant untrained priors.
  8. Recurrent Exposure Generation for Low-Light Face Detection
    Recurrent Exposure Generation for Low-Light Face Detection
    Jinxiu Liang, Jingwen Wang, Yuhui Quan, Tianyi Chen, Jiaying Liu, Haibin Ling, and Yong Xu
    IEEE Transactions on Multimedia (TMM), 2021
    pdf /code
    Multi-exposure imagined from one dark shot makes faces detectable at night.

Funding

  • 2026 · Physics-Constrained Continuous Temporal Field Reconstruction from Asynchronous Event Streams for High-Speed Scene Analysis, JSPS KAKENHI Grant-in-Aid for Early-Career Scientists (PI) [record]
  • 2025 · Generative Neuromorphic Photography for Low-Light High-Speed Scenarios, National Institute of Informatics, Japan (PI)
  • 2023 · Key Technologies of Event-Guided Low-Light High-Speed Photography, National Natural Science Foundation of China (Young Scientists Fund) (PI)
  • 2022 · Uncertainty Modeling for Image Enhancement in Real-World Low-Light Scenarios, China Postdoctoral Science Foundation (PI)

Honors and Awards

Professional Service

Recognition:

  • 2024 · IJCV Outstanding Reviewer Award (1 of only 4) [announcement]
  • 2026 · CVPR Outstanding Reviewer (top 5%) [list]
  • 2026 · ICML Gold Reviewer (top 25%) [list]
  • 2024 · NeurIPS Top Reviewer (top 8%) [list]

Reviewing:

  • Journal: IEEE TPAMI, IJCV, IEEE TIP, IEEE TMM, IEEE TCI, IEEE TCSVT, IEEE TIM, Information Fusion
  • Conference: CVPR (2022–2026), ICCV (2023, 2025), ECCV (2022, 2024, 2026), NeurIPS (2024, 2025), ICML (2025, 2026), ICLR (2024), AAAI (2023, 2025, 2026)

Teaching

Outreach and Leadership

  • 2026 · Presenter, NII Open House poster and demo
  • 2025 · Presenter, NII Open House poster and demo
  • 2015 · Vice President (1 of 6 elected campus-wide), Student Union, South China University of Technology
  • 2015 · Three-Star Volunteer community-service award, South China University of Technology
  • 2011 · Outstanding Student Leader (sole awardee campus-wide), Guangdong Province