{"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/3d-human-pose-estimation-with-relational","title":"3D Human Pose Estimation with Relational Networks","arxiv_id":"1805.08961","date":"2018-05-23","proceeding":null,"authors":["Sungheon Park","Nojun Kwak"],"abstract":"In this paper, we propose a novel 3D human pose estimation algorithm from a\nsingle image based on neural networks. We adopted the structure of the\nrelational networks in order to capture the relations among different body\nparts. In our method, each pair of different body parts generates features, and\nthe average of the features from all the pairs are used for 3D pose estimation.\nIn addition, we propose a dropout method that can be used in relational\nmodules, which inherently imposes robustness to the occlusions. The proposed\nnetwork achieves state-of-the-art performance for 3D pose estimation in Human\n3.6M dataset, and it effectively produces plausible results even in the\nexistence of missing joints.","url_abs":"http://arxiv.org/abs/1805.08961v2","url_pdf":"http://arxiv.org/pdf/1805.08961v2.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":"3d-human-pose-estimation-with-relational","repo_url":"https://github.com/sungheonpark/3D_HPE_RN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"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":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.08961","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}