Learning 3-D Human Pose Estimation from Catadioptric Videos
Learning 3-D Human Pose Estimation from Catadioptric Videos
Chenchen Liu, Yongzhi Li, Kangqi Ma, Duo Zhang, Peijun Bao, Yadong Mu
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Main Track. Pages 852-859.
https://doi.org/10.24963/ijcai.2021/118
3-D human pose estimation is a crucial step for understanding human actions. However, reliably capturing precise 3-D position of human joints is non-trivial and tedious. Current models often suffer from the scarcity of high-quality 3-D annotated training data. In this work, we explore a novel way of obtaining gigantic 3-D human pose data without manual annotations. In catedioptric videos (\emph{e.g.}, people dance before a mirror), the camera records both the original and mirrored human poses, which provides cues for estimating 3-D positions of human joints. Following this idea, we crawl a large-scale Dance-before-Mirror (DBM) video dataset, which is about 24 times larger than existing Human3.6M benchmark. Our technical insight is that, by jointly harnessing the epipolar geometry and human skeleton priors, 3-D joint estimation can boil down to an optimization problem over two sets of 2-D estimations. To our best knowledge, this represents the first work that collects high-quality 3-D human data via catadioptric systems. We have conducted comprehensive experiments on cross-scenario pose estimation and visualization analysis. The results strongly demonstrate the usefulness of our proposed DBM human poses.
Keywords:
Computer Vision: 2D and 3D Computer Vision
Computer Vision: Video: Events, Activities and Surveillance