{"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/a-dual-source-approach-for-3d-pose-estimation","title":"A Dual-Source Approach for 3D Pose Estimation from a Single Image","arxiv_id":"1509.06720","date":"2015-09-22","proceeding":"CVPR 2016 6","authors":["Hashim Yasin","Umar Iqbal","Björn Krüger","Andreas Weber","Juergen Gall"],"abstract":"One major challenge for 3D pose estimation from a single RGB image is the\nacquisition of sufficient training data. In particular, collecting large\namounts of training data that contain unconstrained images and are annotated\nwith accurate 3D poses is infeasible. We therefore propose to use two\nindependent training sources. The first source consists of images with\nannotated 2D poses and the second source consists of accurate 3D motion capture\ndata. To integrate both sources, we propose a dual-source approach that\ncombines 2D pose estimation with efficient and robust 3D pose retrieval. In our\nexperiments, we show that our approach achieves state-of-the-art results and is\neven competitive when the skeleton structure of the two sources differ\nsubstantially.","url_abs":"http://arxiv.org/abs/1509.06720v2","url_pdf":"http://arxiv.org/pdf/1509.06720v2.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":"2d-pose-estimation","task_name":"2D Pose Estimation"},{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"pose-retrieval","task_name":"Pose Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-humaneva-i","task":"3D Human Pose Estimation","dataset":"HumanEva-I","model":"Dual-source approach","rank_in_archive_order":24,"of":31,"metrics":{"Mean Reconstruction Error (mm)":"38.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1509.06720","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}