Hang Su

Ph.D. Student @ ShanghaiTech | Visiting Student @ UPenn GRASP Lab

prof_pic.jpg

My name is Hang Su (苏杭). I am a PhD student at ShanghaiTech University and a member of the Mobile Perception Lab, advised by Prof. Laurent Kneip. I received my B.Eng. in Computer Science from ShanghaiTech University in 2021. I am currently a visiting student at the GRASP Lab, University of Pennsylvania, working with Prof. Kostas Daniilidis.

My research interests lie in 3D Computer Vision and Robotics — building systems that perceive geometry and motion in the real world. I am drawn to Structure-from-Motion and the broader question of how machines recover spatial understanding from raw visual data, combining geometric modeling with learning-based methods.

My current work focuses on event cameras — neuromorphic sensors that capture brightness changes asynchronously at microsecond resolution. They hold great promise for robotic perception under fast motion and challenging lighting — one of many promising directions in 3D vision and robotics.

Selected Publications

  1. arXiv
    match-any-events.png
    Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras
    Ruijun Zhang, Hang Su, Kostas Daniilidis, and 1 more author
    arXiv preprint arXiv:2604.18744, 2025
    arXiv Code
  2. ICCV
    iccv25.png
    A Linear N-Point Solver for Structure and Motion from Asynchronous Tracks
    Hang Su, Yunlong Feng, Daniel Gehrig, and 4 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025 | Highlight (top 9.7%)
    arXiv Video Code
  3. RA-L
    ral24.png
    Motion-Aware Optical Camera Communication with Event Cameras
    Hang Su, Ling Gao, Tao Liu, and 1 more author
    IEEE Robotics and Automation Letters, 2024
    Presented at ICRA 2025
    arXiv Video Code
  4. CVPR
    cvpr24.png
    An N-Point Linear Solver for Line and Motion Estimation with Event Cameras
    Ling Gao, Daniel Gehrig, Hang Su, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 | Oral (top 3.3%)
    arXiv Video Project Page
  5. ICCV
    iccv23.png
    A 5-Point Minimal Solver for Event Camera Relative Motion Estimation
    Ling Gao*, Hang Su*, Daniel Gehrig, and 3 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023 | Oral (top 9%)
    arXiv Video Project Page