publications

publications by categories in reversed chronological order.

2023

  1. ponderv2.png
    arXiv
    PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm
    Haoyi Zhu*, Honghui Yang*, Xiaoyang Wu*, Di Huang*, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, and 3 more authors
    arXiv preprint, 2023
    (* indicates equal contribution)
  2. unipad.png
    arXiv
    UniPAD: A Universal Pre-training Paradigm for Autonomous Driving
    Honghui Yang, Sha Zhang, Di Huang, Xiaoyang Wu, Haoyi Zhu, Tong He, Shixiang Tang, Hengshuang Zhao, and 3 more authors
    arXiv preprint, 2023
  3. sentry crop.png
    NeurIPS
    Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images
    Zeyu Lu*, Di Huang*Lei Bai*Xihui Liu, Jingjing Qu, and Wanli Ouyang
    NeurIPS dataset and benchmark track, 2023
    (* indicates equal contribution)
  4. motiongpt.png
    arXiv
    MotionGPT: Finetuned LLMs are General-Purpose Motion Generators
    Yaqi Zhang, Di Huang, Bin Liu, Shixiang Tang, Yan Lu, Lu Chen, Lei Bai, Qi Chu, and 2 more authors
    arXiv preprint, 2023
  5. ponder.jpeg
    ICCV
    Ponder: Point cloud pre-training via neural rendering
    Di HuangSida PengTong He, Honghui Yang, Xiaowei Zhou, and Wanli Ouyang
    ICCV, 2023

2022

  1. OnePose++.png
    NeurIPS
    Onepose++: Keypoint-free one-shot object pose estimation without CAD models
    Xingyi He, Jiaming Sun, Yuang Wang, Di Huang, Hujun Bao, and Xiaowei Zhou
    NeurIPS, 2022
  2. hhor crop.png
    SiggraphAsia
    Reconstructing hand-held objects from monocular video
    Di Huang, Xiaopeng Ji, Xingyi He, Jiaming Sun, Tong He, Qing Shuai, Wanli Ouyang, and Xiaowei Zhou
    Siggraph Asia, 2022

2021

  1. easymocap.png
    Github
    EasyMoCap - Make human motion capture easier.
    Qing Shuai, Qi Fang, Junting DongSida PengDi Huang, Hujun Bao, and Xiaowei Zhou
    2021