Peizheng Li

Ph.D. student | Machine Learning, Vision, Robotics and Autonomous Driving

prof_pic_new.jpg

Hey there! This is Peizheng Li, a PhD student with the Scene Understanding Group at Mercedes-Benz R&D, as well as the Cognitive Systems Group at University of Tübingen, where I am advised by Prof. Andreas Geiger and Prof. Andreas Zell.

Previously I was a master’s student majoring in Electromobility at the University of Stuttgart, where I completed my research thesis at the Institute of Signal Processing and System Theory, supervised by Prof. Bin Yang. Before that, I received my undergraduate degree in Automotive Studies at Tongji University.

Currently my research interests lie in the intersection of machine learning, robotics and computer vision. In particular, I am interested in extending autonomous driving capability, such as perception, prediction, etc., to real-life open world scenarios.

news

Jun 25, 2025 Our AGO: Adaptive Grounding for Open World 3D Occupancy Prediction paper is accepted by ICCV 2025. 🎉
Jul 01, 2024 Our SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving paper is accepted by ECCV 2024. 🎉 The 1st ranking on Argoverse 2 Self-supervised scene flow leaderboard!
Aug 07, 2023 I will be presenting PowerBEV at ROAD++: The Second Workshop & Challenge on Event Detection for Situation Awareness in Autonomous Driving @ ICCV 2023. Looking forward to meeting you.
Apr 19, 2023 PowerBEV, Our paper on camera-based end-to-end instance prediction in bird’s-eye view, has been accepted by IJCAI 2023. 🎉

selected publications

  1. ICCV 2025
    ago_arch.jpg
    AGO: Adaptive Grounding for Open World 3D Occupancy Prediction
    In International Conference on Computer Vision (ICCV), 2025
  2. ECCV 2024
    seflow_arch.png
    SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving
    In European Conference on Computer Vision (ECCV), 2024
  3. IJCAI 2023
    powerbev_arch.png
    PowerBEV: A Powerful Yet Lightweight Framework for Instance Prediction in Bird’s-Eye View
    In International Joint Conference on Artificial Intelligence (IJCAI), Aug 2023
  4. ArXiv 2025
    tqd_track_arch.jpg
    TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking
    Shuxiao Ding, Yutong Yang, Julian Wiederer, Markus Braun, Peizheng Li, Juergen Gall, and Bin Yang
    arXiv preprint arXiv:2504.03258, Aug 2025
  5. ArXiv 2025
    fam_hri_arch.jpg
    FAM-HRI: Foundation-Model Assisted Multi-Modal Human-Robot Interaction Combining Gaze and Speech
    arXiv preprint arXiv:2503.16492, Aug 2025
  6. ArXiv 2025
    seer_var_arch.png
    SEER-VAR: Semantic Egocentric Environment Reasoner for Vehicle Augmented Reality
    Yuzhi Lai, Shenghai Yuan, Peizheng Li, Jun Lou, and Andreas Zell
    arXiv preprint arXiv:2508.17255, Aug 2025