Xuyang BAI 白旭阳

A 3D Vision Engineer at Apple and contributor for Object Capture. I obtained my PhD degree (2018-2022) in Computer Science and Engineering at HKUST, advised by Prof. Chiew-Lan Tai at Vision and Graphics Group. I also worked closely with Prof. Long Quan and Prof. Hongbo Fu. Prior to HKUST, I received my BSc in Electronic Engenieering from Beijing Normal University.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

profile photo
News

  • 2022.07: Extended version of VMNet is accepted by PAMI.
  • 2022.07: One paper is accepted by ECCV2022.
  • 2022.05: PhD-ed :)
  • 2022.03: Code for TransFusion has been released.
  • 2021.11: Our work TransFusion outperforms all the non-ensembled methods in the leaderboard of nuScenes detection and achieves the 1st place in the leaderboard of nuScenes tracking on open track.
  • Research

    I'm interested in 3D computer vision, machine learning, computer graphics. Specifically, I did some works about building correspondences (for point clouds or images) and scene understanding (detection or segmentation). Free free to drop me an e-mail if you are insterested in my work.

    VMNet_TPAMI2022 Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation of Indoor Scenes
    Zeyu Hu, Xuyang Bai, Jiaxiang Shang, Runze Zhang, Jiayu Dong, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai
    TPAMI, 2022 (ICCV 2021 SI invited)
    paper / code / bibtex
    LiDAL_ECCV2022 LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation
    Zeyu Hu, Xuyang Bai, Runze Zhang, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai
    ECCV, 2022
    paper / code / bibtex
    SGMNet TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers.
    Xuyang Bai, Zeyu Hu, Xinge Zhu, Qingqiu Huang, Yilun Chen, Hongbo Fu, Chiew-Lan Tai
    CVPR, 2022
    paper / code / bibtex
    SGMNet Learning to Match Features with Seeded Graph Matching Network.
    Hongkai Chen, Zixin Luo, Jiahui Zhang, Lei Zhou, Xuyang Bai, Zeyu Hu, Chiew-Lan Tai, Long Quan
    ICCV, 2021
    paper / code / bibtex
    VMNet VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation
    Zeyu Hu, Xuyang Bai, Jiaxiang Shang, Runze Zhang, Jiayu Dong, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai
    ICCV, 2021 (Oral)
    paper / code / bibtex

    SGMNet PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency.
    Xuyang Bai, Zixin Luo, Lei Zhou, Hongkai Chen, Lei Li, Zeyu Hu, Hongbo Fu, Chiew-Lan Tai
    CVPR, 2021
    paper / code / bibtex
    SGMNet JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds.
    Zeyu Hu, Mingmin Zhen, Xuyang Bai, Hongbo Fu, Chiew-lan Tai
    ECCV, 2020
    paper / code / bibtex
    SGMNet ASLFeat: Learning Local Features of Accurate Shape and Localization.
    Zixin Luo, Lei Zhou, Xuyang Bai, Hongkai Chen, Jiahui Zhang, Yao Yao, Shiwei Li, Tian Fang, Long Quan
    CVPR, 2020
    paper / code / bibtex
    SGMNet D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features.
    Xuyang Bai, Zixin Luo, Lei Zhou, Hongbo Fu, Long Quan, Chiew-Lan Tai
    CVPR, 2020 (Oral)
    paper / code / bibtex
    Experience

  • Huawei Intelligent Automotive Solution BU, Mar.2021-Jan.2022
  • Megvii Research ShangHai, Sept.2020-Feb.2021
  • Talks

  • Talk at Zhidx about Multi-Modal 3D Object Detection with Transformers, Spring 2022
  • Talk at 3D视觉工坊 about Feature-matching based Point Cloud Registration, Spring 2021
  • Reviewer Services

  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • European Conference on Computer Vision (ECCV)
  • Pattern Recognition
  • Computers & Graphics

  • Last update: Feb. 2023. Thanks for the template of Jon Barron.