{"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/absolute-human-pose-estimation-with-depth","title":"Absolute Human Pose Estimation with Depth Prediction Network","arxiv_id":"1904.05947","date":"2019-04-11","proceeding":null,"authors":["Márton Véges","András Lőrincz"],"abstract":"The common approach to 3D human pose estimation is predicting the body joint\ncoordinates relative to the hip. This works well for a single person but is\ninsufficient in the case of multiple interacting people. Methods predicting\nabsolute coordinates first estimate a root-relative pose then calculate the\ntranslation via a secondary optimization task. We propose a neural network that\npredicts joints in a camera centered coordinate system instead of a\nroot-relative one. Unlike previous methods, our network works in a single step\nwithout any post-processing. Our network beats previous methods on the\nMuPoTS-3D dataset and achieves state-of-the-art results.","url_abs":"http://arxiv.org/abs/1904.05947v1","url_pdf":"http://arxiv.org/pdf/1904.05947v1.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":"absolute-human-pose-estimation-with-depth","repo_url":"https://github.com/vegesm/depthpose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-multi-person-pose-estimation-absolute-on","task":"3D Multi-Person Pose Estimation (absolute)","dataset":"MuPoTS-3D","model":"Depth Prediction Network","rank_in_archive_order":14,"of":14,"metrics":{"MPJPE":"292"},"uses_additional_data":false},{"leaderboard":"/sota/3d-multi-person-pose-estimation-root-relative","task":"3D Multi-Person Pose Estimation (root-relative)","dataset":"MuPoTS-3D","model":"Depth Prediction Network","rank_in_archive_order":18,"of":20,"metrics":{"MPJPE":"120"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.05947","atlas_url":"https://app.syntology.ai/?focus=1904.05947","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}