{"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/rethinking-pose-in-3d-multi-stage-refinement","title":"Rethinking Pose in 3D: Multi-stage Refinement and Recovery for Markerless Motion Capture","arxiv_id":"1808.01525","date":"2018-08-04","proceeding":null,"authors":["Denis Tome","Matteo Toso","Lourdes Agapito","Chris Russell"],"abstract":"We propose a CNN-based approach for multi-camera markerless motion capture of\nthe human body. Unlike existing methods that first perform pose estimation on\nindividual cameras and generate 3D models as post-processing, our approach\nmakes use of 3D reasoning throughout a multi-stage approach. This novelty\nallows us to use provisional 3D models of human pose to rethink where the\njoints should be located in the image and to recover from past mistakes. Our\nprincipled refinement of 3D human poses lets us make use of image cues, even\nfrom images where we previously misdetected joints, to refine our estimates as\npart of an end-to-end approach. Finally, we demonstrate how the high-quality\noutput of our multi-camera setup can be used as an additional training source\nto improve the accuracy of existing single camera models.","url_abs":"http://arxiv.org/abs/1808.01525v1","url_pdf":"http://arxiv.org/pdf/1808.01525v1.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":[{"paper_slug":"rethinking-pose-in-3d-multi-stage-refinement","repo_url":"https://github.com/MatteoT90/WibergianLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"markerless-motion-capture","task_name":"Markerless Motion Capture"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}