{"url":"/sota/3d-multi-person-pose-estimation-root-relative","task":{"name":"3D Multi-Person Pose Estimation (root-relative)","url":"/task/3d-multi-person-pose-estimation-root-relative","note":null},"dataset":{"name":"MuPoTS-3D","url":"/dataset/mupots-3d"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"This task aims to solve root-relative 3D multi-person pose estimation (person-centric coordinate system). No ground truth human bounding box and human root joint coordinates are used during testing stage.\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":["3DPCK","MPJPE","AUC"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"3DPCK":null,"MPJPE":null,"AUC":"higher"}},"counts":{"rows":20,"rows_with_code":12,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"TDBU_Net","metrics":{"3DPCK":"89.6"},"uses_additional_data":false,"paper_date":"2021-04-05","paper":"/paper/monocular-3d-multi-person-pose-estimation-by","paper_url":"https://arxiv.org/abs/2104.01797v2","paper_title":"Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks","code":"https://github.com/3dpose/3D-Multi-Person-Pose","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"Dual network","metrics":{"3DPCK":"89.6"},"uses_additional_data":false,"paper_date":"2022-05-02","paper":"/paper/dual-networks-based-3d-multi-person-pose","paper_url":"https://arxiv.org/abs/2205.00748v3","paper_title":"Dual networks based 3D Multi-Person Pose Estimation from Monocular Video","code":"https://github.com/3dpose/3D-Multi-Person-Pose","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"GnTCN","metrics":{"3DPCK":"87.5"},"uses_additional_data":false,"paper_date":"2020-12-22","paper":"/paper/graph-and-temporal-convolutional-networks-for","paper_url":"https://arxiv.org/abs/2012.11806v3","paper_title":"Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos","code":"https://github.com/3dpose/GnTCN","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"PIRN","metrics":{"3DPCK":"85.8"},"uses_additional_data":false,"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":5,"model":"Temporal Smoothing","metrics":{"3DPCK":"85.3","MPJPE":"103"},"uses_additional_data":false,"paper_date":"2020-10-31","paper":"/paper/temporal-smoothing-for-3d-human-pose","paper_url":"https://arxiv.org/abs/2011.00250v1","paper_title":"Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded People","code":"https://github.com/vegesm/pose_refinement","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"GR-M3D","metrics":{"3DPCK":"84.6","AUC":"44.1"},"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":7,"model":"HDNet","metrics":{"3DPCK":"83.7"},"uses_additional_data":false,"paper_date":"2020-07-17","paper":"/paper/hdnet-human-depth-estimation-for-multi-person","paper_url":"https://arxiv.org/abs/2007.08943v1","paper_title":"HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization","code":"https://github.com/jiahaoLjh/HumanDepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"POTR-3D","metrics":{"3DPCK":"83.7"},"uses_additional_data":false,"paper_date":"2023-09-15","paper":"/paper/towards-robust-and-smooth-3d-multi-person","paper_url":"https://arxiv.org/abs/2309.08644v1","paper_title":"Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"Cascaded Dimension-Lifting","metrics":{"3DPCK":"83.3"},"uses_additional_data":false,"paper_date":"2021-04-08","paper":"/paper/deep-monocular-3d-human-pose-estimation-via","paper_url":"https://arxiv.org/abs/2104.03520v1","paper_title":"Deep Monocular 3D Human Pose Estimation via Cascaded Dimension-Lifting","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"WDSPose","metrics":{"3DPCK":"82.7"},"uses_additional_data":false,"paper_date":"2020-04-08","paper":"/paper/multi-person-absolute-3d-human-pose","paper_url":"https://arxiv.org/abs/2004.03989v1","paper_title":"Multi-Person Absolute 3D Human Pose Estimation with Weak Depth Supervision","code":"https://github.com/vegesm/wdspose","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"DAS","metrics":{"3DPCK":"82.7"},"uses_additional_data":false,"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":12,"model":"PI-Net","metrics":{"3DPCK":"82.5"},"uses_additional_data":false,"paper_date":"2020-10-11","paper":"/paper/pi-net-pose-interacting-network-for-multi","paper_url":"https://arxiv.org/abs/2010.05302v1","paper_title":"PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"HMOR","metrics":{"3DPCK":"82.0"},"uses_additional_data":false,"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":14,"model":"3DMPPE_POSENET","metrics":{"3DPCK":"81.8"},"uses_additional_data":false,"paper_date":"2019-07-26","paper":"/paper/camera-distance-aware-top-down-approach-for","paper_url":"https://arxiv.org/abs/1907.11346v2","paper_title":"Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image","code":"https://github.com/mks0601/3DMPPE_POSENET_RELEASE","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"Liu et al.","metrics":{"3DPCK":"79.4"},"uses_additional_data":false,"paper_date":"2022-07-29","paper":"/paper/explicit-occlusion-reasoning-for-multi-person","paper_url":"https://arxiv.org/abs/2208.00090v1","paper_title":"Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"SMAP","metrics":{"3DPCK":"73.5"},"uses_additional_data":false,"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":17,"model":"Single-Shot Multi-Person","metrics":{"3DPCK":"65"},"uses_additional_data":false,"paper_date":"2017-12-09","paper":"/paper/single-shot-multi-person-3d-pose-estimation","paper_url":"http://arxiv.org/abs/1712.03453v3","paper_title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","code":"https://github.com/Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch","n_code_links":5,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"Depth Prediction Network","metrics":{"MPJPE":"120"},"uses_additional_data":false,"paper_date":"2019-04-11","paper":"/paper/absolute-human-pose-estimation-with-depth","paper_url":"http://arxiv.org/abs/1904.05947v1","paper_title":"Absolute Human Pose Estimation with Depth Prediction Network","code":"https://github.com/vegesm/depthpose","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"Mehta et al.","metrics":{"MPJPE":"132"},"uses_additional_data":false,"paper_date":"2017-12-09","paper":"/paper/single-shot-multi-person-3d-pose-estimation","paper_url":"http://arxiv.org/abs/1712.03453v3","paper_title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","code":"https://github.com/Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch","n_code_links":5,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"LCR-Net","metrics":{"MPJPE":"146"},"uses_additional_data":false,"paper_date":"2017-07-01","paper":"/paper/lcr-net-localization-classification","paper_url":"http://openaccess.thecvf.com/content_cvpr_2017/html/Rogez_LCR-Net_Localization-Classification-Regression_for_CVPR_2017_paper.html","paper_title":"LCR-Net: Localization-Classification-Regression for Human Pose","code":null,"n_code_links":0,"syntology":null}],"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 6,264 of the 9,581 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":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+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":5,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":5,"n_unverified":9,"n_samples":14,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":6,"n_unverified":10,"n_samples":16,"n_pointer_only_licence":0,"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"}}}