Gu Wang (王谷)

wangg12 at tsinghua dot org dot cn

Google Scholar / ORCID / Semantic Scholar / Aminer / Research Gate / GitHub

About Me

I received my B.E. degree in 2016 and Ph.D. degree in 2022 from Department of Automation, School of Information Science and Technology, Tsinghua University, under the supervision of Prof. Xiangyang Ji. My research interests lie in Computer Vision and Deep Learning. During my Ph.D., I focused on 6D object pose estimation with RGB based methods. I am also interested in other vision and robotics related perception problems in both 2D and 3D worlds.

News

  • [04/2022] I am co-organizing the 7th International Workshop on Recovering 6D Object Pose and BOP Challenge 2022 @ ECCV 22.
  • [02/2022] I joined JD.com as a member of DMT (Doctoral Management Trainee).
  • [12/2021] PhD defended.
  • [08/2020] Our work CDPNv2 won the Best Method on Single Dataset Award of BOP Challenge 2020.
  • [10/2019] Our work CDPN won the Best RGB-Only Method Award of BOP Challenge 2019.

  • Publications

    For all publications please check my Google Scholar / Semantic Scholar / Research Gate.
    (* indicates equal contribution)
    CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement
    Xingyu Liu*, Gu Wang*, Yi Li, Xiangyang Ji
    In European Conference on Computer Vision (ECCV), 2022.
    [Paper][arXiv] [Code] [bibtex]
    Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation
    Gu Wang*, Fabian Manhardt*, Xingyu Liu, Xiangyang Ji, Federico Tombari
    In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021.
    [Paper] [arXiv] [Code] [bibtex]
    SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation
    Yan Di, Fabian Manhardt, Gu Wang, Xiangyang Ji, Nassir Navab, Federico Tombari
    In IEEE International Conference on Computer Vision (ICCV), 2021.
    [Paper] [Code] [bibtex]
    GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation
    Gu Wang, Fabian Manhardt, Federico Tombari, Xiangyang Ji
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
    [Paper] [Code] [bibtex]
    CPS++: Improving Class-level 6D Pose and Shape Estimation From Monocular Images With Self-Supervised Learning
    Fabian Manhardt, Gu Wang, Benjamin Busam, Manuel Nickel, Sven Meier, Luca Minciullo, Xiangyang Ji, Nassir Navab
    arXiv:2003.05848.
    [Paper] [bibtex]
    Self6D: Self-Supervised Monocular 6D Object Pose Estimation
    Gu Wang*, Fabian Manhardt*, Jianzhun Shao, Xiangyang Ji, Nassir Navab, Federico Tombari
    In European Conference on Computer Vision (ECCV), 2020 (oral).
    [Paper] [Diff-Renderer Code] [Video] [bibtex]
    PFRL: Pose-Free Reinforcement Learning for 6D Pose Estimation
    Jianzhun Shao, Yuhang Jiang, Gu Wang, Zhigang Li, Xiangyang Ji
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
    [Paper] [Video] [bibtex]
    CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation
    Zhigang Li, Gu Wang, Xiangyang Ji
    In IEEE International Conference on Computer Vision (ICCV), 2019 (oral).
    [Paper] [Code for BOP19/20] [Oral Video] [bibtex]
    DeepIM: Deep Iterative Matching for 6D Pose Estimation
    Yi Li, Gu Wang, Xiangyang Ji, Yu Xiang, Dieter Fox
    In European Conference on Computer Vision (ECCV), 2018 (oral).
    In International Journal of Computer Vision (IJCV), 2020.
    [Paper] [Code] [Slides] [Project Page] [bibtex]

    Experience

    Service