个人简介
程文灿，博士，现任中山大学人工智能学院副教授、博士生导师，此前在新加坡国立大学担任博士后研究员。硕士和博士均毕业于韩国成均馆大学人工智能学院。主要从事具身智能与三维计算机视觉方向研究，重点关注三维场景运动理解、手-物交互感知以及高效人工智能模型部署等关键问题
近年来，发表了多篇包括CVPR, ICCV, AAAI,ECCV等CCF A/B类会议在内的学术论文。长期担任多个CCF A类会议和期刊审稿人，包括CVPR, ICCV, AAAI, TPAMI, TIP,TCSVT，IJCV等。
工作经历
· 2026.5-至今，中山大学，人工智能学院，副教授
· 2024.04-2025.04，新加坡国立大学，计算机学院，博士后
研究与招生
研究领域：具身智能与三维计算机视觉，主要研究内容包含人机交互、手物交互、模型压缩加速等。
欢迎有意申请中山大学硕士研究生、科研助理、访问实习生，以及有意向提前参与科研的中山大学本科生与我联系。邮箱：chengwc1260@163.com
论文成果
1.Wencan Cheng and Gim Hee Lee. "HandMCM: Multi-modal Point Cloud-based Correspondence State Space Model for 3D Hand Pose Estimation", The Association for the Advancement of Artificial Intelligence (AAAI). 2025. (CCF-A, acceptance rate: 17.6%)
2.Wencan Cheng, Eunji Kim and Jong Hwan Ko. "HandDAGT: A Denoising Adaptive Graph Transformer for 3D Hand Pose Estimation", European Conference on Computer Vision (ECCV). 2024. (CCF-B, acceptance rate: 27.9%)
3.Wencan Cheng, Hao Tang, Luc Van Gool and Jong Hwan Ko. "HandDiff: 3D Hand Pose Estimation with Diffusion on Point Cloud", Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR, highlight). 2024. (CCF-A, highlight acceptance rate: 3.6%)
4.Wencan Cheng and Jong Hwan Ko. "Multi-Scale Bidirectional Recurrent Network with Hybrid Correlation for Point Cloud Based Scene Flow Estimation" IEEE/CVF International Conference Conference on Computer Vision (ICCV). 2023. (CCF-A, acceptance rate:26.8%)
5.Wencan Cheng and Jong Hwan Ko. "HandR2N2: Iterative 3D Hand Pose Estimation Using a Residual Recurrent Neural Network" IEEE/CVF International Conference Conference on Computer Vision (ICCV). 2023. (CCF-A, acceptance rate:26.8%)
6.Wencan Cheng (通讯) and Jong Hwan Ko. "Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation." European Conference on Computer Vision (ECCV oral). Cham: Springer Nature Switzerland, 2022. (CCF-B, oral acceptance rate:2.8%)
7.Wencan Cheng, Jae Hyun Park, and Jong Hwan Ko. "HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeleton." Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2021. (CCF-A, acceptance rate:25.9%)
