Jinpeng Liu

I am a Ph.D. student at the National University of Singapore (NUS), advised by Prof. Xingyu Liu. Previously, I received my M.S. from Tsinghua University (THU), advised by Prof. Yansong Tang, and my B.S. in Intelligence Science and Technology from Sun Yat-sen University (SYSU) in 2022.

If you are interested in discussing research or potential collaborations, please feel free to EMAIL me.

My current research focuses on robots and computer vision.

Email  /  Github  /  Linkedin  /  Google Scholar

profile photo
News

  • 2026-02: A paper is accepted to CVPR 2026.
  • 2025-11: A paper is accepted to TPAMI.
  • 2025-06: A paper is accepted to ICCV 2025.
  • 2025-08: Started my Ph.D. at the National University of Singapore.
  • 2024-07: Two papers are accepted to ECCV 2024.
  • 2023-12: Start an internship at Tencent ARC Lab.
  • 2023-02: A paper is accepted to CVPR 2023.
  • 2022-11: A paper is accepted to AAAI 2023.
  • Publications and Preprints

    * indicates equal contribution

    TROPHIES TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos
    Jinpeng Liu, Yukang Xu, Yutong Li, Xingyu Liu
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
    [Paper] [Project Page] [Code]
    FLAG3D++ FLAG3D++: A Benchmark for 3D Fitness Activity Comprehension with Language Instruction
    Yansong Tang, Aoyang Liu, Jinpeng Liu, Shiyi Zhang, Wenxun Dai,
    Jie Zhou, Xiu Li, Jiwen Lu
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
    [Paper] [Project Page] [Code]
    ScoreHOI ScoreHOI: Physically Plausible Reconstruction of Human-Object Interaction via Score-Guided Diffusion
    Ao Li, Jinpeng Liu, Yixuan Zhu, Yansong Tang
    IEEE/CVF International Conference on Computer Vision (ICCV), 2025
    [Paper] [Project Page] [Code]
    dise NovelGS: Consistent Novel-view Denoising via Large Gaussian Reconstruction Model
    Jinpeng Liu, Jiale Xu, Weihao Cheng, Yiming Gao, Xintao Wang, Ying Shan,
    Yansong Tang
    Preprint, 2024
    [Paper] [Project Page] [Code]
    dise Plan, Posture and Go: Towards Open-World Text-to-Motion Generation
    Jinpeng Liu*, Wenxun Dai*, Chunyu Wang*, Yiji Cheng, Yansong Tang, Xin Tong
    The European Conference on Computer Vision (ECCV), 2024
    [Paper] [Project Page]
    dise FLAG3D: A 3D Fitness Activity Dataset with Language Instruction
    Yansong Tang (M.S. Advisor)*, Jinpeng Liu*, Aoyang Liu*, Bin Yang, Wenxun Dai,
    Yongming Rao, Jie Zhou, Jiwen Lu, Xiu Li
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
    [Paper] [Project Page] [Code]
    dise MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model
    Wenxun Dai, Linghao Chen, Jingbo Wang, Jinpeng Liu, Bo Dai, Yansong Tang,
    The European Conference on Computer Vision (ECCV), 2024
    [Paper] [Project Page] [Code]
    dise Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense
    for COVID-19 Detection

    Kun Xiang, Xing Zhang, Jinwen She, Jinpeng Liu, Haohan Wang, Shiqi Deng,
    Shancheng Jiang,
    The Association for the Advancement of Artificial Intelligence (AAAI), 2023
    [Paper] [Project Page] [Code]

    Industrial Experience

    dise Tencent ARC Lab, Shenzhen, China. December 2023–May 2024.
  • Project: 3D Object Generation, e.g., InstantMesh (4.6k GitHub stars), among others.
  • Work with Dr. Jiale Xu, Dr. Xintao Wang, and Dr. Ying Shan.
  • dise Microsoft Research - Asia (MSRA), Beijing, China. April-December, 2023.
  • Project: Human Motion Understanding and Generation.
  • Work with Dr. Chunyu Wang, Dr. Xin Tong.

  • Activities

  • Conference Reviewer: CVPR 2026, NeurIPS 2026, CVPR 2025 (Outstanding Reviewer), CVPR 2024, FG 2023

  • Website Template

    © Jinpeng Liu | Last updated: Oct. 9, 2026