arXiv preprint / 6D位姿

VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions

作者：Yash Garg, Saketh Bachu, Arindam Dutta, Rohit Lal, Sarosij Bose, Calvin-Khang Ta, M. Salman Asif, Riverside @ucr.edu · 单位：Yash Garg, Saketh Bachu, Arindam Dutta, Rohit Lal, M. Salman Asif, Amit Roy-Chowdhury, University of California, Riverside · 会议/期刊：arXiv preprint · 方向：6D位姿 · 发布日期：2025-08-09

6D位姿估计人体姿态数据集/基准
新标签打开 AlphaXiv新标签打开 Project
VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions figure
AlphaXiv 中文概览（可滚动查看）