{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mo2cap2-real-time-mobile-3d-motion-capture","title":"Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera","arxiv_id":"1803.05959","date":"2018-03-15","proceeding":null,"authors":["Weipeng Xu","Avishek Chatterjee","Michael Zollhoefer","Helge Rhodin","Pascal Fua","Hans-Peter Seidel","Christian Theobalt"],"abstract":"We propose the first real-time approach for the egocentric estimation of 3D\nhuman body pose in a wide range of unconstrained everyday activities. This\nsetting has a unique set of challenges, such as mobility of the hardware setup,\nand robustness to long capture sessions with fast recovery from tracking\nfailures. We tackle these challenges based on a novel lightweight setup that\nconverts a standard baseball cap to a device for high-quality pose estimation\nbased on a single cap-mounted fisheye camera. From the captured egocentric live\nstream, our CNN based 3D pose estimation approach runs at 60Hz on a\nconsumer-level GPU. In addition to the novel hardware setup, our other main\ncontributions are: 1) a large ground truth training corpus of top-down fisheye\nimages and 2) a novel disentangled 3D pose estimation approach that takes the\nunique properties of the egocentric viewpoint into account. As shown by our\nevaluation, we achieve lower 3D joint error as well as better 2D overlay than\nthe existing baselines.","url_abs":"http://arxiv.org/abs/1803.05959v2","url_pdf":"http://arxiv.org/pdf/1803.05959v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"egocentric-pose-estimation","task_name":"Egocentric Pose Estimation"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/egocentric-pose-estimation-on-globalegomocap","task":"Egocentric Pose Estimation","dataset":"GlobalEgoMocap Test Dataset","model":"Mo2Cap2","rank_in_archive_order":6,"of":7,"metrics":{"Average MPJPE (mm)":"102.3","PA-MPJPE":"74.46"},"uses_additional_data":true},{"leaderboard":"/sota/egocentric-pose-estimation-on-sceneego","task":"Egocentric Pose Estimation","dataset":"SceneEgo","model":"Mo2Cap2","rank_in_archive_order":7,"of":8,"metrics":{"Average MPJPE (mm)":"200.3","PA-MPJPE":"121.2"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1803.05959","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}