Photo

Jiehong Lin (林杰鸿)


I am currently a postdoctoral research fellow in the Computer Vision and Machine Intelligence Lab (CVMI Lab) at the University of Hong Kong, under the supervision of Prof. Xiaojuan Qi. Prior to this, I obtained my Ph.D. degree from the South China University of Technology in June 2023, under the supervision of Prof. Kui Jia. Before pursuing my Ph.D., I received a BEng degree from the South China University of Technology.

Research Field: Computer Vision | 3D Semantic Analysis | Robotics Learning

Email: mortimer.jh.lin@gmail.com; lin.jiehong @ mail.scut.edu.cn

Other Link: [Google Scholar] [Github]

News



  • [07/2024] NEW I have been a Postdoc in Dept. EEE at HKU.

  • [03/2024] Our work SAM-6D for zero-shot 6D object pose estimation gets accepted to CVPR 2024. [Paper][Code]

  • [07/2023] One paper gets accepted to ICCV 2023.

  • [06/2023] I obtain my Ph.D. degree.

  • [04/2023] One paper gets accepted to IJCAI 2023.

  • Experiences


    2024.07 - present

    The University of Hong Kong, Hong Kong, China
    Postdoctoral Fellow, Advisor: Prof. Xiaojuan Qi
    Department of Electrical and Electronic Engineering (EEE)

    2024.02 - 2024.06

    The Chinese University of Hong Kong, Shenzhen, China
    Research Assistant
    School of Data Science (SDS)

    2022.03 - 2024.01

    DexForce Technology Co. Ltd, Shenzhen, China
    Algorithm Intern
    Research and Development Department

    2019.09 - 2020.01

    University of Macau, Macau, China
    Research Assistant
    State Key Laboratory of Internet of Things for Smart City

    2017.09 - 2023.06

    South China University of Technology, Guangzhou, China
    Ph.D, Advisor: Prof. Kui Jia
    Electronic and Information Engineering

    2013.09 - 2017.06

    South China University of Technology, Guangzhou, China
    Bachelor of Engineering
    Electronic and Information Engineering

    Pre-Prints


    Point-MA2E: Masked and Affine Transformed AutoEncoder for Self-supervised Point Cloud Learning
    Under submission.
    Masked Surfel Prediction for Self-Supervised Point Cloud Learning
    Under submission.
    CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsampling
    Under submission.

    Publications


    SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation
    Jiehong Lin*, Lihua Liu*, Dekun Lu, Kui Jia (* joint first authors)
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2024
    VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations
    Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2023
    Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Pose
    International Joint Conference on Artificial Intelligence Organization (IJCAI). 2023
    Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks
    European Conference on Computer Vision (ECCV). 2022
    DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation
    Hongyang Li*, Jiehong Lin*, Kui Jia (* joint first authors)
    European Conference on Computer Vision (ECCV). 2022
    Sparse Steerable Convolutions: An Efficient Learning of SE (3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space
    Jiehong Lin*, Hongyang Li*, Jiangbo Lu, Kui Jia (* joint first authors)
    Advances in Neural Information Processing Systems (NeurIPS). 2021
    DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency
    Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2021
    Geometry-Aware Generation of Adversarial Point Clouds
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2020
    Deep Multi-View Learning using Neuron-Wise Correlation-Maximizing Regularizers
    IEEE Transactions on Image Processing (TIP). 2019

    Services



    Reviewers: CVPR, ICCV, ECCV, ICML, ICLR, NeurIPS, TIP, TMM, TCSVT, TMLR.