{"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/real-time-2d-multi-person-pose-estimation-on","title":"Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose","arxiv_id":"1811.12004","date":"2018-11-29","proceeding":null,"authors":["Daniil Osokin"],"abstract":"In this work we adapt multi-person pose estimation architecture to use it on\nedge devices. We follow the bottom-up approach from OpenPose, the winner of\nCOCO 2016 Keypoints Challenge, because of its decent quality and robustness to\nnumber of people inside the frame. With proposed network design and optimized\npost-processing code the full solution runs at 28 frames per second (fps) on\nIntel$\\unicode{xAE}$ NUC 6i7KYB mini PC and 26 fps on Core$^{TM}$ i7-6850K CPU.\nThe network model has 4.1M parameters and 9 billions floating-point operations\n(GFLOPs) complexity, which is just ~15% of the baseline 2-stage OpenPose with\nalmost the same quality. The code and model are available as a part of\nIntel$\\unicode{xAE}$ OpenVINO$^{TM}$ Toolkit.","url_abs":"http://arxiv.org/abs/1811.12004v1","url_pdf":"http://arxiv.org/pdf/1811.12004v1.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":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/2xic/openpose-pigs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/Daniil-Osokin/lightweight-human-pose-estimation.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/ModelBunker/Lightweight-OpenPose-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/Rocketbase-AI/rockets-lightpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/hsk9767/open_pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/murdockhou/lightweight_openpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/omkarbhope/Pose-Estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/tyIceStream/lightweight-human-pose-estimation.OpenCV","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"multi-person-pose-estimation","task_name":"Multi-Person Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"pc","method_name":"pc"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.12004","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}