Papers

2025

  1. richcontrol.png
    RichControl: Structure- and Appearance-Rich Training-Free Spatial Control for Text-to-Image Generation
    Liheng Zhang*, Lexi Pang*, Hang Ye, Xiaoxuan Ma, and Yizhou Wang
    arXiv 2025
    Paper Video Code Project Page
  2. geneman.gif
    GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data
    Wentao Wang*, Hang Ye*, Fangzhou Hong, Xue Yang, Jianfu Zhang, Yizhou Wang, Ziwei Liu, and Liang Pan
    Neural Information Processing Systems (NeurIPS), 2025
    Paper Video Code Project Page
  3. freecloth.gif
    Free-form Generation Enhances Challenging Clothed Human Modeling
    Hang Ye, Xiaoxuan Ma, Hai Ci, Wentao Zhu, and Yizhou Wang
    Conference on Computer Vision and Pattern Recognition (CVPR), 2025  (Highlight)
    Paper Video Code Project Page

2024

    2023

    1. social-ch_teaser.gif
      Social Motion Prediction with Cognitive Hierarchies
      Wentao Zhu*, Jason Qin*, Yuke Lou, Hang Ye, Xiaoxuan Ma, Hai Ci, and Yizhou Wang
      Neural Information Processing Systems (NeurIPS), 2023
      Paper Video Code Project Page
    2. dmae.png
      Denoising Masked AutoEncoders are Certifiable Robust Vision Learners
      Quanlin Wu, Hang Ye, Yuntian Gu, Huishuai Zhang, Liwei Wang, and Di He
      International Conference on Learning Representations (ICLR), 2023
      Paper Code

    2022

    1. faster-voxelpose.jpeg
      Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection
      Hang Ye*, Wentao Zhu*, Chunyu Wang, Rujie Wu, and Yizhou Wang
      European Conference on Computer Vision (ECCV), 2022
      Paper Code
    2. guided_diff.png
      Guided Diffusion Model for Adversarial Purification from Random Noise
      Quanlin Wu, Hang Ye, and Yuntian Gu
      Technical report, arXiv:2206.10875, 2022
      Paper