{"url":"/sota/3d-multi-person-pose-estimation-on-cmu","task":{"name":"3D Multi-Person Pose Estimation","url":"/task/3d-multi-person-pose-estimation","note":null},"dataset":{"name":"Panoptic","url":"/dataset/cmu-panoptic"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"This task aims to solve root-relative 3D multi-person pose estimation. No human bounding box and root joint coordinate groundtruth are used in testing time.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [RootNet](https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Average MPJPE (mm)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average MPJPE (mm)":null}},"counts":{"rows":20,"rows_with_code":12,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":17},"rows":[{"rank_in_archive_order":1,"model":"TesseTrack","metrics":{"Average MPJPE (mm)":"7.3"},"uses_additional_data":true,"paper_date":"2021-06-16","paper":"/paper/tessetrack-end-to-end-learnable-multi-person","paper_url":"http://www.cs.cmu.edu/~ILIM/projects/IM/TesseTrack/","paper_title":"TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"PRGN","metrics":{"Average MPJPE (mm)":"15.68"},"uses_additional_data":true,"paper_date":"2021-09-13","paper":"/paper/graph-based-3d-multi-person-pose-estimation","paper_url":"https://arxiv.org/abs/2109.05885v1","paper_title":"Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images","code":"https://github.com/wusize/multiview_pose","n_code_links":1,"syntology":{"n_ran":19,"n_unverified":3,"n_samples":22,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"MvP","metrics":{"Average MPJPE (mm)":"15.8"},"uses_additional_data":true,"paper_date":"2021-11-07","paper":"/paper/direct-multi-view-multi-person-3d-pose","paper_url":"https://arxiv.org/abs/2111.04076v2","paper_title":"Direct Multi-view Multi-person 3D Pose Estimation","code":"https://github.com/openxrlab/xrmocap","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"PlaneSweepPose","metrics":{"Average MPJPE (mm)":"16.75"},"uses_additional_data":true,"paper_date":"2021-04-06","paper":"/paper/multi-view-multi-person-3d-pose-estimation","paper_url":"https://arxiv.org/abs/2104.02273v1","paper_title":"Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo","code":"https://github.com/jiahaoLjh/PlaneSweepPose","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"VoxelPose","metrics":{"Average MPJPE (mm)":"17.68"},"uses_additional_data":true,"paper_date":"2020-04-13","paper":"/paper/end-to-end-estimation-of-multi-person-3d","paper_url":"https://arxiv.org/abs/2004.06239v4","paper_title":"VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment","code":"https://github.com/open-mmlab/mmpose","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"Faster VoxelPose","metrics":{"Average MPJPE (mm)":"18.41"},"uses_additional_data":true,"paper_date":"2022-07-22","paper":"/paper/faster-voxelpose-real-time-3d-human-pose","paper_url":"https://arxiv.org/abs/2207.10955v1","paper_title":"Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection","code":"https://github.com/AlvinYH/Faster-VoxelPose","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":7,"model":"VoxelTrack","metrics":{"Average MPJPE (mm)":"18.49"},"uses_additional_data":true,"paper_date":"2021-08-05","paper":"/paper/voxeltrack-multi-person-3d-human-pose","paper_url":"https://arxiv.org/abs/2108.02452v1","paper_title":"VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"QuickPose","metrics":{"Average MPJPE (mm)":"29.4"},"uses_additional_data":true,"paper_date":"2022-07-22","paper":"/paper/quickpose-real-time-multi-view-multi-person","paper_url":"https://dl.acm.org/doi/abs/10.1145/3528233.3530746","paper_title":"QuickPose: Real-time Multi-view Multi-person Pose Estimation in Crowded Scenes","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"RapidPoseTriangulation (without training)","metrics":{"Average MPJPE (mm)":"30.5"},"uses_additional_data":false,"paper_date":"2025-03-27","paper":"/paper/rapidposetriangulation-multi-view-multi","paper_url":"https://arxiv.org/abs/2503.21692v1","paper_title":"RapidPoseTriangulation: Multi-view Multi-person Whole-body Human Pose Triangulation in a Millisecond","code":"https://gitlab.com/Percipiote/RapidPoseTriangulation","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"Light3DPose","metrics":{"Average MPJPE (mm)":"38.59"},"uses_additional_data":true,"paper_date":"2020-04-06","paper":"/paper/light3dpose-real-time-multi-person-3d","paper_url":"https://arxiv.org/abs/2004.02688v1","paper_title":"Light3DPose: Real-time Multi-Person 3D PoseEstimation from Multiple Views","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"IVT (f=5)","metrics":{"Average MPJPE (mm)":"48.4"},"uses_additional_data":true,"paper_date":"2022-08-06","paper":"/paper/ivt-an-end-to-end-instance-guided-video","paper_url":"https://arxiv.org/abs/2208.03431v1","paper_title":"IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"PIRN","metrics":{"Average MPJPE (mm)":"49.8"},"uses_additional_data":true,"paper_date":"2022-04-11","paper":"/paper/permutation-invariant-relational-network-for","paper_url":"https://arxiv.org/abs/2204.04913v2","paper_title":"Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"MVG","metrics":{"Average MPJPE (mm)":"50"},"uses_additional_data":true,"paper_date":"2020-07-21","paper":"/paper/multi-person-3d-pose-estimation-in-crowded","paper_url":"https://arxiv.org/abs/2007.10986v1","paper_title":"Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry","code":"https://github.com/HeCraneChen/3D-Crowd-Pose-Estimation-Based-on-MVG","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":19,"n_samples":19,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"HMOR","metrics":{"Average MPJPE (mm)":"51.6"},"uses_additional_data":true,"paper_date":"2020-08-01","paper":"/paper/hmor-hierarchical-multi-person-ordinal","paper_url":"https://arxiv.org/abs/2008.00206v2","paper_title":"HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"DAS","metrics":{"Average MPJPE (mm)":"53.8"},"uses_additional_data":true,"paper_date":"2022-03-15","paper":"/paper/distribution-aware-single-stage-models-for","paper_url":"https://arxiv.org/abs/2203.07697v4","paper_title":"Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation","code":"https://github.com/wangzt-halo/das","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"GR-M3D","metrics":{"Average MPJPE (mm)":"57.9"},"uses_additional_data":false,"paper_date":"2022-07-22","paper":"/paper/dynamic-graph-reasoning-for-multi-person-3d","paper_url":"https://arxiv.org/abs/2207.11341v2","paper_title":"Dynamic Graph Reasoning for Multi-person 3D Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"VirtualPose","metrics":{"Average MPJPE (mm)":"58.9"},"uses_additional_data":true,"paper_date":"2022-07-20","paper":"/paper/virtualpose-learning-generalizable-3d-human","paper_url":"https://arxiv.org/abs/2207.09949v1","paper_title":"VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data","code":"https://github.com/wkom/virtualpose","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"SMAP","metrics":{"Average MPJPE (mm)":"61.8"},"uses_additional_data":true,"paper_date":"2020-08-26","paper":"/paper/smap-single-shot-multi-person-absolute-3d","paper_url":"https://arxiv.org/abs/2008.11469v1","paper_title":"SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation","code":"https://github.com/zju3dv/smap","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"InstanceHMR","metrics":{"Average MPJPE (mm)":"126.1"},"uses_additional_data":true,"paper_date":"2024-01-01","paper":"/paper/instance-aware-contrastive-learning-for","paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Gwon_Instance-aware_Contrastive_Learning_for_Occluded_Human_Mesh_Reconstruction_CVPR_2024_paper.html","paper_title":"Instance-aware Contrastive Learning for Occluded Human Mesh Reconstruction","code":"https://github.com/dcvl-3d/instancehmr_release","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"BMP","metrics":{"Average MPJPE (mm)":"135.4"},"uses_additional_data":false,"paper_date":"2021-05-06","paper":"/paper/body-meshes-as-points","paper_url":"https://arxiv.org/abs/2105.02467v2","paper_title":"Body Meshes as Points","code":"https://github.com/jfzhang95/BMP","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":7,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":32,"n_unverified":33,"n_samples":65,"n_pointer_only_licence":4,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":32,"n_unverified":33,"n_samples":65,"n_pointer_only_licence":4,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}