{"type":"ScholarlyArticle","title":"Learning 3-D Human Pose Estimation from Catadioptric Videos","authors":[{"name":"Chenchen Liu","slug":"chenchen-liu","given":"Chenchen","family":"Liu","affiliation":""},{"name":"Yongzhi Li","slug":"yongzhi-li","given":"Yongzhi","family":"Li","affiliation":""},{"name":"Kangqi Ma","slug":"kangqi-ma","given":"Kangqi","family":"Ma","affiliation":""},{"name":"Duo Zhang","slug":"duo-zhang","given":"Duo","family":"Zhang","affiliation":""},{"name":"Peijun Bao","slug":"peijun-bao","given":"Peijun","family":"Bao","affiliation":""},{"name":"Yadong Mu","slug":"yadong-mu","given":"Yadong","family":"Mu","affiliation":""}],"abstract":"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.","doi":"10.24963/ijcai.2021/118","url":"https://ijcai.org/proceedings/2021/118","pdf":"https://ijcai.org/proceedings/2021/0118.pdf","markdown":"https://ijcai.org/proceedings/2021/118.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/118","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Computer Vision I","track":"Main Track","number":118,"pages":{"first":852,"last":859},"keywords":["Computer Vision: 2D and 3D Computer Vision","Computer Vision: Video: Events, Activities and Surveillance"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}