{"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/single-shot-multi-person-3d-pose-estimation","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","arxiv_id":"1712.03453","date":"2017-12-09","proceeding":null,"authors":["Dushyant Mehta","Oleksandr Sotnychenko","Franziska Mueller","Weipeng Xu","Srinath Sridhar","Gerard Pons-Moll","Christian Theobalt"],"abstract":"We propose a new single-shot method for multi-person 3D pose estimation in\ngeneral scenes from a monocular RGB camera. Our approach uses novel\nocclusion-robust pose-maps (ORPM) which enable full body pose inference even\nunder strong partial occlusions by other people and objects in the scene. ORPM\noutputs a fixed number of maps which encode the 3D joint locations of all\npeople in the scene. Body part associations allow us to infer 3D pose for an\narbitrary number of people without explicit bounding box prediction. To train\nour approach we introduce MuCo-3DHP, the first large scale training data set\nshowing real images of sophisticated multi-person interactions and occlusions.\nWe synthesize a large corpus of multi-person images by compositing images of\nindividual people (with ground truth from mutli-view performance capture). We\nevaluate our method on our new challenging 3D annotated multi-person test set\nMuPoTs-3D where we achieve state-of-the-art performance. To further stimulate\nresearch in multi-person 3D pose estimation, we will make our new datasets, and\nassociated code publicly available for research purposes.","url_abs":"http://arxiv.org/abs/1712.03453v3","url_pdf":"http://arxiv.org/pdf/1712.03453v3.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":"single-shot-multi-person-3d-pose-estimation","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":"single-shot-multi-person-3d-pose-estimation","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":"single-shot-multi-person-3d-pose-estimation","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":"single-shot-multi-person-3d-pose-estimation","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":"single-shot-multi-person-3d-pose-estimation","repo_url":"https://github.com/ataata107/Research-Papers-Implementations/tree/master/Single-shot%20multi%20person%203d%20body%20pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"3d-multi-person-pose-estimation-absolute","task_name":"3D Multi-Person Pose Estimation (absolute)"},{"task_slug":"3d-multi-person-pose-estimation-root-relative","task_name":"3D Multi-Person Pose Estimation (root-relative)"},{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[{"slug":"muco-3dhp","name":"MuCo-3DHP","full_name":""},{"slug":"mupots-3d","name":"MuPoTS-3D","full_name":"Multiperson Pose Test Set in 3DMulti-person Pose estimation Test Set in 3D"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-mpi-inf-3dhp","task":"3D Human Pose Estimation","dataset":"MPI-INF-3DHP","model":"Single-Shot Multi-Person","rank_in_archive_order":80,"of":108,"metrics":{"AUC":"37.8","MPJPE":"122.2","PCK":"75.2"},"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":"Single-Shot Multi-Person","rank_in_archive_order":17,"of":20,"metrics":{"3DPCK":"65"},"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":"Mehta et al.","rank_in_archive_order":19,"of":20,"metrics":{"MPJPE":"132"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.03453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.03453"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ModelBunker/Lightweight-OpenPose-PyTorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ataata107/Research-Papers-Implementations/tree/master/Single-shot%20multi%20person%203d%20body%20pose","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2xic/openpose-pigs","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/omkarbhope/Pose-Estimation","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"dea6a8a2a18bbd85","entry":"convert_to_coco_format","repo":"ModelBunker/Lightweight-OpenPose-PyTorch","repo_kind":"listed","path":"val.py","file_url":"https://github.com/ModelBunker/Lightweight-OpenPose-PyTorch/blob/HEAD/val.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dea6a8a2a18bbd85"}},{"code_sha256_prefix":"c79acdb155994f2a","entry":"normalize","repo":"ModelBunker/Lightweight-OpenPose-PyTorch","repo_kind":"listed","path":"val.py","file_url":"https://github.com/ModelBunker/Lightweight-OpenPose-PyTorch/blob/HEAD/val.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c79acdb155994f2a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}