Xiaoyang Bai

WeLight Lab at the University of Hong Kong

my_profile_v2.jpg

301 Haking Wong Building

The University of Hong Kong

I am currently a Postdoctoral Fellow at WeLight Lab, Department of Electrical and Computer Engineering, HKU. I am fortunate to be supervised by Prof. Evan Y. Peng.

I received my Ph.D. degree in Computer Science from University of Illinois Urbana-Champaign in 2024, advised by Prof. Alexander Schwing and mentored by Prof. Viktor Gruev and Prof. David Forsyth. Before that, I completed my undergraduate study at University of California, Berkeley, where I majored in Computer Science, Applied Mathematics, Cognitive Science and Linguistics.

My research interests span the fields of Computer Vision, Computer Graphics and Computational Optics. I am particularly attracted to the idea of physically-grounded 3D perception and world reconstruction with unconventional visual modalities (event stream, polarization image, etc.). My non-research interests include science (or more generally, speculative/fantasy) fictions, zoos and gaming.

news

Oct 17, 2026 I am honored to serve as the Organization Chair for the Pacific Graphics 2027!
Jun 03, 2026 One paper has been accepted by TVCG.
Apr 09, 2026 Our paper PhyGaP: Physically-Grounded Gaussians with Polarization Cues have been selected as Award Candidate and Oral Presentation for CVPR 2026!
Feb 23, 2026 One paper has been accepted by CVMJ.
Feb 21, 2026 Two papers have been accepted by CVPR 2026.

selected publications

  1. cvmj_erf_teaser.png
    ERF-GS: Reconstructing Fast Motion from Disjoint Event-RGB Viewpoints
    Xiaoyang Bai, Zhenyang Li, Weiwei Xu , and 2 more authors
    Computational Visual Media, 2026
  2. cvpr_uw_teaser.png
    Global Underwater Geolocation from Time-Lapse Polarization Imagery
    Sara Aghajanzadeh, Xiaoyang Bai, Zhongmin Zhu , and 2 more authors
    In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2026
  3. cvpr_polar_teaser.png
    PhyGaP: Physically-Grounded Gaussians with Polarization Cues
    Jiale Wu, Xiaoyang Bai, Zongqi He , and 2 more authors
    In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2026
  4. eventtracer_teaser.png
    EventTracer: Fast Path Tracing-based Event Stream Rendering
    Zhenyang Li, Xiaoyang Bai, Jinfan Lu , and 3 more authors
    IEEE Transactions on Visualization and Computer Graphics, 2026
  5. 3dv_teaser.png
    Structure-grounded Training Strategies Aid Generalization in Stereo Matching
    Liangxun Ou, Yuhui Liu, Zhenyang Li , and 2 more authors
    In Proceedings of International Conference on 3D Vision , 2026
  6. ismar_teaser.png
    Enhanced Velocity Field Modeling for Gaussian Video Reconstruction
    Zhenyang Li*, Xiaoyang Bai*, Tongchen Zhang , and 3 more authors
    In Proceedings of IEEE International Symposium on Mixed and Augmented Realitys (ISMAR) , 2025
  7. vc_teaser.png
    Learning RGBD imaging via asymmetrically focused stereo cameras
    Liangxun Ou, Yuhui Liu, Xiaoyang Bai , and 1 more author
    The Visual Computer, 2025
  8. sectran_teaser.jpg
    Learning a global underwater geolocalization model with sectoral transformer
    Xiaoyang Bai, Zhongmin Zhu, Alexander Schwing , and 2 more authors
    Optics Express, 2024
  9. elight_teaser2.png
    Polarization-based underwater geolocalization with deep learning
    Xiaoyang Bai, Zuodong Liang, Zhongmin Zhu , and 3 more authors
    eLight, 2023