董浩业

副教授

联系邮箱： donghy28@mail.sysu.edu.cn

个人主页： https://www.haoyed.com/

教师简介

董浩业，副教授、博士生导师、国家级青年人才、逸仙优秀学者。博士毕业于raybet电竞下载，曾在美国卡内基梅隆大学、新加坡国立大学从事博士后及高级研究员工作。主要面向三维视觉与具身智能开展研究，重点关注三维人体建模、多模态人—场景交互学习，以及世界模型驱动的人形机器人感知、决策与控制。近年来在 NeurIPS、CVPR 等顶级会议发表多篇论文，担任 NeurIPS、ICLR、CVPR 等领域主席，组织三届 CVPR Workshop 国际研讨会。

欢迎对人形机器人、三维视觉、具身智能、多模态大模型等方向感兴趣的同学加入团队。

招生对象：2026/2027 年 9 月入学硕士生、博士生
支持与资源：优秀学生可推荐至 CMU、NUS、TikTok、NVIDIA 等海内外高校/企业深造、访学或实习；团队提供充足计算资源和机器人实验平台。

 

研究领域

人形机器人移动操作（Humanoid Loco-Manipulation）、具身世界模型、多模态人与场景交互建模、三维视觉


海外经历

2022.09-- 2024.08，美国卡内基梅隆大学（CMU） | 机器人研究所 | Postdoctoral Fellow

2024.09-- 2026.06，新加坡国立大学（NUS）         | 计算机学院    | Senior Research Fellow 

 

代表性论著

  1. Haoye Dong and Gim Hee Lee. “PS-Mamba: Spatial-Temporal Graph Mamba for Pose Sequence Refinement.” In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025. [第一作者｜CCF A]
  2. Aviral Chharia, Wenbo Gou, and Haoye Dong*. “MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation.” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. [通讯作者｜CCF A]
  3. Haoye Dong, Aviral Chharia, Wenbo Gou, Francisco Vicente Carrasco, and Fernando De la Torre. “Hamba: Single-View 3D Hand Reconstruction with Graph-Guided Bi-Scanning Mamba.” In Advances in Neural Information Processing Systems (NeurIPS), 2024. [第一作者｜CCF A]
  4. Haoye Dong, Jun Liu, and Dong Huang. “Universal Monocular 3D Human Recovery Engine.” In Proceedings of the IEEE International Conference on Robotics and Automation, Video Track (ICRA Video Track), 2024. [第一作者｜CCF B]
  5. Haoye Dong, Tiange Xiang, Sravan Chittupalli, Jun Liu, and Dong Huang. “Physical-Space Multi-Body Mesh Detection Achieved by Local Alignment and Global Dense Learning.” the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1267–1276, 2024. [第一作者]
  6. Haoye Dong, Jun Liu, and Dong Huang. “DF-VTON: Dense Flow Guided Virtual Try-On Network.” In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024. [第一作者｜CCF B]
  7. Haoyuan Li*, Haoye Dong*, Hanchao Jia, Dong Huang, Michael C. Kampffmeyer, Liang Lin, and Xiaodan Liang. “Coordinate Transformer: Achieving Single-Stage Multi-Person Mesh Recovery from Videos.” In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 7744–7753, 2023. [共同第一作者｜CCF A]
  8. Haoye Dong, Xiaodan Liang, Xiaohui Shen, Zhenyu Xie, Jian Yin, et al. “Fashion Editing with Adversarial Parsing Learning.” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8120–8128, 2020. [第一作者｜CCF A]
  9. Haoye Dong, Xiaodan Liang, Xiaohui Shen, Bochao Wang, Hanjiang Lai, Jia Zhu, Zhiting Hu, and Jian Yin. “Towards Multi-Pose Guided Virtual Try-On Network.” In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 9026–9035, 2019. [第一作者｜CCF A]
  10. Haoye Dong, Xiaodan Liang, Xiaohui Shen, Bowen Wu, Bing-Cheng Chen, and Jian Yin. “FW-GAN: Flow-Navigated Warping GAN for Video Virtual Try-On.” In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1161–1170, 2019. [第一作者｜CCF A]
  11. Haoye Dong, Xiaodan Liang, Chenxing Zhou, Hanjiang Lai, Jia Zhu, and Jian Yin. “Part-Preserving Pose Manipulation for Person Image Synthesis.” In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), pp. 1234–1239, 2019. [第一作者｜CCF B]
  12. Haoye Dong, Xiaodan Liang, Ke Gong, Hanjiang Lai, Jia Zhu, and Jian Yin. “Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis.” In Advances in Neural Information Processing Systems (NeurIPS), pp. 472–482, 2018. [第一作者｜CCF A]

 

 

实验室小伙伴

实验室小伙伴