{"url":"/sota/3d-hand-pose-estimation-on-ho-3d","task":{"name":"3D Hand Pose Estimation","url":"/task/3d-hand-pose-estimation","note":null},"dataset":{"name":"HO-3D v2","url":"/dataset/ho-3d"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Image: [Zimmerman et l](https://arxiv.xsrg/pdf/1705.01389v3.pdf)","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":["PA-MPJPE (mm)","PA-MPVPE","F@5mm","F@15mm","AUC_J","AUC_V"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"PA-MPJPE (mm)":null,"PA-MPVPE":null,"F@5mm":null,"F@15mm":null,"AUC_J":"higher","AUC_V":"higher"}},"counts":{"rows":24,"rows_with_code":19,"rows_with_paper_page":24,"rows_dated":24,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"ExtPose (T=16)","metrics":{"AUC_J":"0.863","AUC_V":"0.856","F@15mm":"0.991","F@5mm":"0.667","PA-MPJPE (mm)":"6.9","PA-MPVPE":"7.3"},"uses_additional_data":false,"paper_date":"2025-06-18","paper":"/paper/extpose-robust-and-coherent-pose-estimation","paper_url":"https://openreview.net/forum?id=hm9FNEZZ6z","paper_title":"ExtPose: Robust and Coherent Pose Estimation by Extending ViTs","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Hamba","metrics":{"AUC_J":"0.850","AUC_V":"0.846","F@15mm":"0.982","F@5mm":"0.648","PA-MPJPE (mm)":"7.5","PA-MPVPE":"7.7"},"uses_additional_data":false,"paper_date":"2024-07-12","paper":"/paper/hamba-single-view-3d-hand-reconstruction-with","paper_url":"https://arxiv.org/abs/2407.09646v2","paper_title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","code":"https://github.com/humansensinglab/Hamba","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":3,"model":"WiLoR","metrics":{"AUC_J":"0.851","AUC_V":"0.846","F@15mm":"0.983","F@5mm":"0.646","PA-MPJPE (mm)":"7.5","PA-MPVPE":"7.7"},"uses_additional_data":false,"paper_date":"2024-09-18","paper":"/paper/wilor-end-to-end-3d-hand-localization-and","paper_url":"https://arxiv.org/abs/2409.12259v2","paper_title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","code":"https://github.com/rolpotamias/WiLoR","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"HaMeR","metrics":{"AUC_J":"0.846","AUC_V":"0.841","F@15mm":"0.980","F@5mm":"0.635","PA-MPJPE (mm)":"7.7","PA-MPVPE":"7.9"},"uses_additional_data":false,"paper_date":"2023-12-08","paper":"/paper/reconstructing-hands-in-3d-with-transformers","paper_url":"https://arxiv.org/abs/2312.05251v1","paper_title":"Reconstructing Hands in 3D with Transformers","code":"https://github.com/geopavlakos/hamer","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"HandBooster","metrics":{"AUC_J":"0.836","AUC_V":"0.832","F@15mm":"0.972","F@5mm":"0.585","PA-MPJPE (mm)":"8.2","PA-MPVPE":"8.4"},"uses_additional_data":false,"paper_date":"2024-03-27","paper":"/paper/handbooster-boosting-3d-hand-mesh","paper_url":"https://arxiv.org/abs/2403.18575v1","paper_title":"HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions","code":"https://github.com/hxwork/handbooster_pytorch","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":0,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"AMVUR","metrics":{"AUC_J":"0.835","AUC_V":"0.836","F@15mm":"0.965","F@5mm":"0.608","PA-MPJPE (mm)":"8.3","PA-MPVPE":"8.2"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/a-probabilistic-attention-model-with","paper_url":"https://arxiv.org/abs/2304.14299v1","paper_title":"A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Image","code":"https://github.com/zhehengjianglancaster/amvur","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"H2ONet","metrics":{"AUC_J":"0.829","AUC_V":"0.828","F@15mm":"0.966","F@5mm":"0.570","PA-MPJPE (mm)":"8.5","PA-MPVPE":"8.6"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/h2onet-hand-occlusion-and-orientation-aware","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Xu_H2ONet_Hand-Occlusion-and-Orientation-Aware_Network_for_Real-Time_3D_Hand_Mesh_Reconstruction_CVPR_2023_paper.html","paper_title":"H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction","code":"https://github.com/hxwork/H2ONet_Pytorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"SemGCN","metrics":{"PA-MPJPE (mm)":"8.8"},"uses_additional_data":false,"paper_date":"2024-03-04","paper":"/paper/3d-hand-reconstruction-via-aggregating-intra","paper_url":"https://arxiv.org/abs/2403.01733v1","paper_title":"3D Hand Reconstruction via Aggregating Intra and Inter Graphs Guided by Prior Knowledge for Hand-Object Interaction Scenario","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"HFL-Net","metrics":{"F@15mm":"0.965","F@5mm":"0.575","PA-MPJPE (mm)":"8.9","PA-MPVPE":"8.7"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/harmonious-feature-learning-for-interactive","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Lin_Harmonious_Feature_Learning_for_Interactive_Hand-Object_Pose_Estimation_CVPR_2023_paper.html","paper_title":"Harmonious Feature Learning for Interactive Hand-Object Pose Estimation","code":"https://github.com/lzfff12/hfl-net","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"HandOccNet","metrics":{"AUC_J":"0.819","AUC_V":"0.819","F@15mm":"0.963","F@5mm":"0.564","PA-MPJPE (mm)":"9.1","PA-MPVPE":"8.8"},"uses_additional_data":false,"paper_date":"2022-03-28","paper":"/paper/handoccnet-occlusion-robust-3d-hand-mesh","paper_url":"https://arxiv.org/abs/2203.14564v1","paper_title":"HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network","code":null,"n_code_links":0,"syntology":{"n_ran":6,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":11,"model":"MobRecon","metrics":{"F@15mm":"0.957","F@5mm":"0.538","PA-MPJPE (mm)":"9.2","PA-MPVPE":"9.4"},"uses_additional_data":false,"paper_date":"2021-12-06","paper":"/paper/mobrecon-mobile-friendly-hand-mesh","paper_url":"https://arxiv.org/abs/2112.02753v2","paper_title":"MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image","code":"https://github.com/SeanChenxy/HandMesh","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"HOISDF","metrics":{"PA-MPJPE (mm)":"9.2"},"uses_additional_data":false,"paper_date":"2024-02-26","paper":"/paper/hoisdf-constraining-3d-hand-object-pose","paper_url":"https://arxiv.org/abs/2402.17062v1","paper_title":"HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields","code":"https://github.com/amathislab/hoisdf","n_code_links":1,"syntology":{"n_ran":16,"n_unverified":7,"n_samples":23,"n_pointer_only_licence":23}},{"rank_in_archive_order":13,"model":"I2UV-HandNet","metrics":{"AUC_J":"0.804","AUC_V":"0.799","F@15mm":"0.943","F@5mm":"0.500","PA-MPJPE (mm)":"9.9","PA-MPVPE":"10.1"},"uses_additional_data":false,"paper_date":"2021-02-07","paper":"/paper/sr-affine-high-quality-3d-hand-model","paper_url":"https://arxiv.org/abs/2102.03725v2","paper_title":"I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modeling","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"DMA","metrics":{"PA-MPJPE (mm)":"10.1"},"uses_additional_data":true,"paper_date":"2022-11-16","paper":"/paper/interacting-hand-object-pose-estimation-via","paper_url":"https://arxiv.org/abs/2211.08805v1","paper_title":"Interacting Hand-Object Pose Estimation via Dense Mutual Attention","code":"https://github.com/rongakowang/densemutualattention","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"SHO","metrics":{"PA-MPJPE (mm)":"10.1"},"uses_additional_data":false,"paper_date":"2021-06-09","paper":"/paper/semi-supervised-3d-hand-object-poses","paper_url":"https://arxiv.org/abs/2106.05266v1","paper_title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","code":"https://github.com/stevenlsw/Semi-Hand-Object","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"METRO","metrics":{"AUC_J":"0.792","AUC_V":"0.779","F@15mm":"0.946","F@5mm":"0.484","PA-MPJPE (mm)":"10.4","PA-MPVPE":"11.1"},"uses_additional_data":false,"paper_date":"2020-12-17","paper":"/paper/end-to-end-human-pose-and-mesh-reconstruction","paper_url":"https://arxiv.org/abs/2012.09760v3","paper_title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","code":"https://github.com/microsoft/MeshTransformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"Hampali et al.","metrics":{"AUC_J":"0.788","AUC_V":"0.790","F@15mm":"0.942","F@5mm":"0.506","PA-MPJPE (mm)":"10.7","PA-MPVPE":"10.6"},"uses_additional_data":false,"paper_date":"2019-07-02","paper":"/paper/ho-3d-a-multi-user-multi-object-dataset-for","paper_url":"https://arxiv.org/abs/1907.01481v6","paper_title":"HOnnotate: A method for 3D Annotation of Hand and Object Poses","code":"https://github.com/shreyashampali/ho3d","n_code_links":4,"syntology":null},{"rank_in_archive_order":18,"model":"KPT-Transformer","metrics":{"AUC_J":"0.786","PA-MPJPE (mm)":"10.8"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/handsformer-keypoint-transformer-for","paper_url":"https://arxiv.org/abs/2104.14639v2","paper_title":"Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation","code":"https://github.com/shreyashampali/kypt_transformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"I2L-MeshNet","metrics":{"AUC_J":"0.775","AUC_V":"0.722","F@15mm":"0.932","F@5mm":"0.409","PA-MPJPE (mm)":"11.2","PA-MPVPE":"13.9"},"uses_additional_data":false,"paper_date":"2020-08-09","paper":"/paper/i2l-meshnet-image-to-lixel-prediction-network-1","paper_url":"https://arxiv.org/abs/2008.03713v2","paper_title":"I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image","code":"https://github.com/mks0601/I2L-MeshNet_RELEASE","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"ArtiBoost","metrics":{"AUC_J":"0.773","AUC_V":"0.782","F@15mm":"0.944","F@5mm":"0.488","PA-MPJPE (mm)":"11.4","PA-MPVPE":"10.9"},"uses_additional_data":false,"paper_date":"2021-09-12","paper":"/paper/artiboost-boosting-articulated-3d-hand-object","paper_url":"https://arxiv.org/abs/2109.05488v2","paper_title":"ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis","code":"https://github.com/mvig-sjtu/artiboost","n_code_links":2,"syntology":null},{"rank_in_archive_order":21,"model":"S2Hand","metrics":{"AUC_J":"0.773","AUC_V":"0.777","F@15mm":"0.930","F@5mm":"0.450","PA-MPJPE (mm)":"11.4","PA-MPVPE":"11.2"},"uses_additional_data":false,"paper_date":"2021-03-22","paper":"/paper/model-based-3d-hand-reconstruction-via-self","paper_url":"https://arxiv.org/abs/2103.11703v1","paper_title":"Model-based 3D Hand Reconstruction via Self-Supervised Learning","code":"https://github.com/TerenceCYJ/S2HAND","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":22,"model":"HOR","metrics":{"PA-MPJPE (mm)":"12.0"},"uses_additional_data":false,"paper_date":"2021-08-16","paper":"/paper/towards-unconstrained-joint-hand-object","paper_url":"https://arxiv.org/abs/2108.07044v2","paper_title":"Towards unconstrained joint hand-object reconstruction from RGB videos","code":"https://github.com/hassony2/homan","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"Pose2Mesh","metrics":{"AUC_J":"0.754","AUC_V":"0.749","F@15mm":"0.909","F@5mm":"0.441","PA-MPJPE (mm)":"12.5","PA-MPVPE":"12.7"},"uses_additional_data":false,"paper_date":"2020-08-20","paper":"/paper/pose2mesh-graph-convolutional-network-for-3d","paper_url":"https://arxiv.org/abs/2008.09047v3","paper_title":"Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose","code":"https://github.com/hongsukchoi/Pose2Mesh_RELEASE","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"Tse et al.","metrics":{"F@15mm":"0.943","F@5mm":"0.485","PA-MPVPE":"10.9"},"uses_additional_data":false,"paper_date":"2022-04-27","paper":"/paper/collaborative-learning-for-hand-and-object","paper_url":"https://arxiv.org/abs/2204.13062v1","paper_title":"Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution","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":9,"rows_with_any_sample_ran":8,"distinct_papers_with_graph_line":9,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":50,"n_unverified":34,"n_samples":84,"n_pointer_only_licence":49,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":50,"n_unverified":34,"n_samples":84,"n_pointer_only_licence":49,"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"}}}