{"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/robust-estimation-of-3d-human-poses-from-a","title":"Robust Estimation of 3D Human Poses from a Single Image","arxiv_id":"1406.2282","date":"2014-06-09","proceeding":"CVPR 2014 6","authors":["Chunyu Wang","Yizhou Wang","Zhouchen Lin","Alan L. Yuille","Wen Gao"],"abstract":"Human pose estimation is a key step to action recognition. We propose a\nmethod of estimating 3D human poses from a single image, which works in\nconjunction with an existing 2D pose/joint detector. 3D pose estimation is\nchallenging because multiple 3D poses may correspond to the same 2D pose after\nprojection due to the lack of depth information. Moreover, current 2D pose\nestimators are usually inaccurate which may cause errors in the 3D estimation.\nWe address the challenges in three ways: (i) We represent a 3D pose as a linear\ncombination of a sparse set of bases learned from 3D human skeletons. (ii) We\nenforce limb length constraints to eliminate anthropomorphically implausible\nskeletons. (iii) We estimate a 3D pose by minimizing the $L_1$-norm error\nbetween the projection of the 3D pose and the corresponding 2D detection. The\n$L_1$-norm loss term is robust to inaccurate 2D joint estimations. We use the\nalternating direction method (ADM) to solve the optimization problem\nefficiently. Our approach outperforms the state-of-the-arts on three benchmark\ndatasets.","url_abs":"http://arxiv.org/abs/1406.2282v1","url_pdf":"http://arxiv.org/pdf/1406.2282v1.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-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-humaneva-i","task":"3D Human Pose Estimation","dataset":"HumanEva-I","model":"Wang et al.","rank_in_archive_order":29,"of":31,"metrics":{"Mean Reconstruction Error (mm)":"71.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1406.2282","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}