FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions

arXiv:2309.05073v4 Announce Type: replace
Abstract: Estimating the 3D structure of the human body from natural scenes is a fundamental aspect of visual perception. 3D human pose estimation is a vital step in advancing fields like AIGC and human-robot interaction, serving as a crucial technique for understanding and interacting with human actions in real-world settings. However, the current datasets, often collected under single laboratory conditions using complex motion capture equipment and unvarying backgrounds, are insufficient. The absence of datasets on variable …

arxiv benchmarking cs.cv human type world