Qingwen Zhang

Ph.D. student, School of Electrical Engineering and Computer Science, KTH

head.jpg

Hi there 👋. Welcome to Qingwen Zhang (张清文) / Kin Zhang (张聪明) Page. I’m a Ph.D. student at the DIVISION OF ROBOTICS, PERCEPTION AND LEARNING at KTH Royal Institute of Technology, supervised by Prof. Patric Jensfelt and Prof. Olov Andersson. My Ph.D. research interests mainly focus on Self-Supervised Understanding of Dynamic Scenes supported by WASP.

Before that, I graduated with an MPhil from the Robotics Institute RAMLAB of Hong Kong University of Science and Technology, supervised by Prof. Ming Liu and Prof. Wei Zhang. My MPhil research interests mainly include planning and end to end learning in autonomous driving.

I am currently seeking full-time opportunities following my upcoming PhD graduation. If you are interested in my research, please feel free to contact me.

News

Feb 23, 2026 Two of our papers: TeFlow and FVGen are accepted by CVPR 2026. :sparkles:.
Sep 18, 2025 Our DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method paper is accepted by NeurIPS 2025, and it’s spotlight. ! :sparkles:.
Aug 20, 2025 Our HiMo: High-Speed Objects Motion Compensation in Point Clouds paper is accepted by Transactions on Robotics (T-RO). :sparkles:.
Jul 1, 2025 Our AGO: Adaptive Grounding for Open World 3D Occupancy Prediction paper is accepted by ICCV 2025. :sparkles:.

Selected Publications

* means co-first authors

2026

  1. teflow.png
    CVPR 2026
    TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation
    Qingwen ZhangChenhan Jiang, Xiaomeng Zhu, Yunqi Miao, Yushan Zhang, Olov Andersson, and Patric Jensfelt
    In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2026
  2. fvgen-v3.png
    CVPR 2026
    FVGen: Scaling 3D Scene Datasets with Certainty-Aware Free-View Generation from Scene Geometry Reconstruction
    Chenhan JiangYu ChenQingwen Zhang, Jifei Song, Songcen Xu, Dit-Yan Yeung, and Jiankang Deng
    In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2026
  3. dogflow.png
    RAL 2026
    DoGFlow: Self-Supervised LiDAR Scene Flow via Cross-Modal Doppler Guidance
    Ajinkya KhocheQingwen ZhangYixi Cai, Sina Sharif Mansouri, and Patric Jensfelt
    IEEE Robotics and Automation Letters, 2026

2025

  1. deltaflow.png
    NeurIPS 2025 (Spotlight)
    DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method
    Qingwen Zhang, Xiaomeng Zhu, Yushan Zhang, Yixi CaiOlov Andersson, and Patric Jensfelt
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
  2. himo.png
    TRO 2025
    HiMo: High-Speed Objects Motion Compensation in Point Clouds
    Qingwen ZhangAjinkya Khoche, Yi Yang, Li Ling, Sina Sharif Mansouri, Olov Andersson, and Patric Jensfelt
    IEEE Transactions on Robotics, 2025

2024

  1. seflow.png
    ECCV 2024
    SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving
    Qingwen Zhang, Yi Yang, Peizheng LiOlov Andersson, and Patric Jensfelt
    In European Conference on Computer Vision (ECCV), 2024
  2. dufomap.png
    RA-L 2024
    DUFOMap: Efficient Dynamic Awareness Mapping
    Daniel Duberg*, Qingwen Zhang*, MingKai Jia, and Patric Jensfelt
    IEEE Robotics and Automation Letters, 2024
  3. deflow.png
    ICRA 2024
    DeFlow: Decoder of Scene Flow Network in Autonomous Driving
    Qingwen Zhang, Yi Yang, Heng Fang, Ruoyu Geng, and Patric Jensfelt
    In 2024 IEEE International Conference on Robotics and Automation (ICRA), 2024

2023

  1. dynaben.png
    ITSC 2023
    A Dynamic Points Removal Benchmark in Point Cloud Maps
    Qingwen Zhang, Daniel Duberg, Ruoyu Geng, Mingkai Jia, Lujia Wang, and Patric Jensfelt
    In IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), 2023
  2. ndem.png
    RAL 2023
    Real-Time Neural Dense Elevation Mapping for Urban Terrain With Uncertainty Estimations
    Bowen YangQingwen Zhang, Ruoyu Geng, Lujia Wang, and Ming Liu
    IEEE Robotics and Automation Letters, 2023

2022

  1. mmfn.png
    IROS 2022
    MMFN: Multi-Modal-Fusion-Net for End-to-End Driving
    Qingwen Zhang, Mingkai Tang, Ruoyu Geng, Feiyi Chen, Ren Xin, and Lujia Wang
    In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022

Service

  • KTH-RPL GPU Cluster Admin Group Member, Check our cluster-wiki
  • Reviewer Service: RA-L, ICRA, IROS, NeurIPS, ICCV

Awards

Bachelor
National Scholarships and First-Class Scholarships for THREE consecutive years
Bachelor
TOP 10 Students for 2020 graduation at Civil Aviation University of China.
Bachelor

2019 Outstanding college students and 2017 Outstanding athletes in Tianjin, China