{"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/orinet-a-fully-convolutional-network-for-3d","title":"OriNet: A Fully Convolutional Network for 3D Human Pose Estimation","arxiv_id":"1811.04989","date":"2018-11-12","proceeding":null,"authors":["Chenxu Luo","Xiao Chu","Alan Yuille"],"abstract":"In this paper, we propose a fully convolutional network for 3D human pose\nestimation from monocular images. We use limb orientations as a new way to\nrepresent 3D poses and bind the orientation together with the bounding box of\neach limb region to better associate images and predictions. The 3D\norientations are modeled jointly with 2D keypoint detections. Without\nadditional constraints, this simple method can achieve good results on several\nlarge-scale benchmarks. Further experiments show that our method can generalize\nwell to novel scenes and is robust to inaccurate bounding boxes.","url_abs":"http://arxiv.org/abs/1811.04989v1","url_pdf":"http://arxiv.org/pdf/1811.04989v1.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":"orinet-a-fully-convolutional-network-for-3d","repo_url":"https://github.com/chenxuluo/OriNet-demo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-mpi-inf-3dhp","task":"3D Human Pose Estimation","dataset":"MPI-INF-3DHP","model":"OriNet","rank_in_archive_order":102,"of":108,"metrics":{"AUC":"32.1","PCK":"64.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.04989","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}