Wayne Wu

wayne_wu.jpg

I am a Research Associate in the Department of Computer Science at the University of California, Los Angeles, working with Bolei Zhou. Previously, I served as a Research Scientist at Shanghai AI Lab, where I led the Virtual Human Group. I was also a Visiting Scholar at Nanyang Technological University, working with Chen Change Loy. In June 2022, I obtained my PhD in the Department of Computer Science and Technology at Tsinghua University.

Research

My research lies at the intersection of computer vision, computer graphics, and machine learning. My goal is to develop Human-centric Embodied AI Systems that promote urban mobility, safety, and accessibility, by addressing key challenges in scalability of agent learning environments, as well as realism and situationality of populated virtual humans. This effort is pursued through three primary directions:

  • Scalable Embodied AI Simulators: Building large-scale robot learning platforms with diverse assets and infinite urban scenes, and enabling high-efficiency training, as in MetaUrban, UrbanSim, Vid2Sim, and OmniObject3D.
  • Realistic Virtual Humans: Constructing high-fidelity 4D volumetric capture systems and datasets, as in DNA-Rendering and RenderMe-360; and developing human foundation models to obtain generalizable representations, as in CosmicMan and MotionBert.
  • Situational Motion Generation: Learning context-aware generative models of human motions and behaviors from diverse modalities -- including vision, audio, and language, as in PedGen, EmbodiedHuman, and Everybody's Talkin'.

News

Jan, 2025 MetaUrban – a simulation platform for Embodied AI in urban spaces, is released. Try it now!
Mar, 2024 We are now organizing the first workshop on Virtual Humans for Robotics and Autonomous Driving @CVPR 2024.
Jun, 2023 OmniObject3D is selected as Best Paper Candidate at CVPR 2023.
Oct, 2022 I am leading OpenXDLab – a new large-scale open-source data platform!
Aug, 2020 We are organizing DeeperForensics Challenge on Real-World Face Forgery Detection, ECCV 2020.
Aug, 2020 We are organizing Workshop on Sensing, Understanding and Synthesizing Humans, ECCV 2020.
Jul, 2020 We released MMAction2, OpenMMLab’s Next Generation Action Understanding Toolbox.
Jul, 2020 We released MMEditing, OpenMMLab’s Image and Video Editing Toolbox.

Selected Publications

  1. Towards Autonomous Micromobility through Scalable Urban Simulation
    Wayne Wu *, Honglin He*, Chaoyuan Zhang, Jack He, Seth Z. Zhao, Ran Gong, Quanyi Li, and Bolei Zhou
    Technical report, coming soon, 2025
  2. Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
    Ziyang Xie, Zhizheng Liu, Zhenghao Peng,  Wayne Wu, and Bolei Zhou
    Technical report, arXiv:2501.06693, 2025
    arXiv Project Page
  3. MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility
    Wayne Wu *, Honglin He*, Jack He, Yiran Wang, Chenda Duan, Zhizheng Liu, Quanyi Li, and Bolei Zhou
    International Conference on Learning Representations (ICLR), 2025
    arXiv YouTube Project Page
  4. CosmicMan: A Text-to-Image Foundation Model for Humans
    Shikai Li, Jianglin Fu, Kaiyuan Liu, Wentao Wang, Kwan-Yee Lin, and Wayne Wu †
    Computer Vision and Pattern Recognition (CVPR), 2024
    arXiv YouTube Project Page
  5. RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars
    Contributors to RenderMe-360
    Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks, 2023
    arXiv YouTube Project Page
  6. DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering
    Contributors to DNA-Rendering
    International Conference on Computer Vision (ICCV), 2023
    arXiv YouTube Project Page
  7. SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling
    Zhitao Yang, Zhongang Cai, Haiyi Mei, Shuai Liu, Zhaoxi Chen, Weiye Xiao, Yukun Wei, Zhongfei Qing, Chen Wei, Bo Dai,  Wayne Wu, Chen Qian, Dahua Lin, Ziwei Liu, and Lei Yang
    International Conference on Computer Vision (ICCV), 2023
    arXiv YouTube Project Page
  8. OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
    Tong Wu, Jiarui Zhang, Xiao Fu, Yuxin Wang, Jiawei Ren, Liang Pan,  Wayne Wu, Lei Yang, Jiaqi Wang, Chen Qian, Dahua Lin, and Ziwei Liu
    Conference on Computer Vision and Pattern Recognition (CVPR), 2023
    arXiv Project Page
  9. StyleGAN-Human: A Data-Centric Odyssey of Human Generation
    Jianglin Fu, Shikai Li, Yuming Jiang, Kwan-Yee Lin, Chen Qian, Chen Change Loy,  Wayne Wu†, and Ziwei Liu
    European Conference on Computer Vision (ECCV), 2022
    arXiv YouTube Project Page
  10. TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
    Wayne Wu, Kaidi Cao, Cheng Li, Chen Qian, and Chen Change Loy
    Conference on Computer Vision and Pattern Recognition (CVPR), 2019
    arXiv YouTube Project Page
  11. ReenactGAN: Learning to Reenact Faces via Boundary Transfer
    Wayne Wu, Yunxuan Zhang, Cheng Li, Chen Qian, and Chen Change Loy
    European Conference on Computer Vision (ECCV), 2018
    arXiv YouTube Project Page
  12. Look at Boundary: A Boundary-Aware Face Alignment Algorithm
    Wayne Wu, Chen Qian, Shuo Yang, Quan Wang, Yici Cai, and Qiang Zhou
    Conference on Computer Vision and Pattern Recognition (CVPR), 2018
    arXiv YouTube Project Page