{"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/learning-3d-human-pose-from-structure-and","title":"Learning 3D Human Pose from Structure and Motion","arxiv_id":"1711.09250","date":"2017-11-25","proceeding":"ECCV 2018 9","authors":["Rishabh Dabral","Anurag Mundhada","Uday Kusupati","Safeer Afaque","Abhishek Sharma","Arjun Jain"],"abstract":"3D human pose estimation from a single image is a challenging problem,\nespecially for in-the-wild settings due to the lack of 3D annotated data. We\npropose two anatomically inspired loss functions and use them with a\nweakly-supervised learning framework to jointly learn from large-scale\nin-the-wild 2D and indoor/synthetic 3D data. We also present a simple temporal\nnetwork that exploits temporal and structural cues present in predicted pose\nsequences to temporally harmonize the pose estimations. We carefully analyze\nthe proposed contributions through loss surface visualizations and sensitivity\nanalysis to facilitate deeper understanding of their working mechanism. Our\ncomplete pipeline improves the state-of-the-art by 11.8% and 12% on Human3.6M\nand MPI-INF-3DHP, respectively, and runs at 30 FPS on a commodity graphics\ncard.","url_abs":"http://arxiv.org/abs/1711.09250v2","url_pdf":"http://arxiv.org/pdf/1711.09250v2.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":"learning-3d-human-pose-from-structure-and","repo_url":"https://github.com/anuragmundhada/3dpose-demo-iitb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"torch","reach":null}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"monocular-3d-human-pose-estimation","task_name":"Monocular 3D Human Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-3dpw","task":"3D Human Pose Estimation","dataset":"3DPW","model":"TP-Net","rank_in_archive_order":111,"of":119,"metrics":{"PA-MPJPE":"92.2"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-3d-human-pose-estimation-on-human3","task":"Monocular 3D Human Pose Estimation","dataset":"Human3.6M","model":"TP-Net","rank_in_archive_order":26,"of":52,"metrics":{"Average MPJPE (mm)":"52.1","Frames Needed":"20","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.09250","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}