{"url":"/task/3d-hand-pose-estimation","name":"3D Hand Pose Estimation","slug":"3d-hand-pose-estimation","description_markdown":"Image: [Zimmerman et l](https://arxiv.xsrg/pdf/1705.01389v3.pdf)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":178,"papers_with_code":87,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":20,"subtasks":3,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/3d-hand-pose-estimation-on-freihand","slug":"3d-hand-pose-estimation-on-freihand","dataset":"FreiHAND","dataset_url":"/dataset/freihand","rows_in_archive":33,"metrics":["PA-MPJPE","PA-MPVPE","PA-F@5mm","PA-F@15mm"],"first_row_in_archive_order":{"model":"ExtPose","paper_title":"ExtPose: Robust and Coherent Pose Estimation by Extending ViTs","paper_url":"/paper/extpose-robust-and-coherent-pose-estimation","paper_date":"2025-06-18","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-hand-pose-estimation-on-ho-3d","slug":"3d-hand-pose-estimation-on-ho-3d","dataset":"HO-3D v2","dataset_url":"/dataset/ho-3d","rows_in_archive":24,"metrics":["PA-MPJPE (mm)","PA-MPVPE","F@5mm","F@15mm","AUC_J","AUC_V"],"first_row_in_archive_order":{"model":"ExtPose (T=16)","paper_title":"ExtPose: Robust and Coherent Pose Estimation by Extending ViTs","paper_url":"/paper/extpose-robust-and-coherent-pose-estimation","paper_date":"2025-06-18","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-hand-pose-estimation-on-h3wb","slug":"3d-hand-pose-estimation-on-h3wb","dataset":"H3WB","dataset_url":"/dataset/h3wb","rows_in_archive":15,"metrics":["Average MPJPE (mm)"],"first_row_in_archive_order":{"model":"SemGAN","paper_title":"3D WholeBody Pose Estimation based on Semantic Graph Attention Network and Distance Information","paper_url":"/paper/3d-wholebody-pose-estimation-based-on-1","paper_date":"2024-06-03","arxiv_id":"2406.01196","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-hand-pose-estimation-on-dexycb","slug":"3d-hand-pose-estimation-on-dexycb","dataset":"DexYCB","dataset_url":"/dataset/dexycb","rows_in_archive":11,"metrics":["Average MPJPE (mm)","Procrustes-Aligned MPJPE","MPVPE","VAUC","PA-MPVPE","PA-VAUC"],"first_row_in_archive_order":{"model":"HOISDF","paper_title":"HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields","paper_url":"/paper/hoisdf-constraining-3d-hand-object-pose","paper_date":"2024-02-26","arxiv_id":"2402.17062","code_links":[{"title":"amathislab/hoisdf","url":"https://github.com/amathislab/hoisdf"}],"syntology":{"n":23,"n_ran":16,"n_unverified":7,"n_pointer_only":23}}},{"leaderboard":"/sota/3d-hand-pose-estimation-on-hint-hand","slug":"3d-hand-pose-estimation-on-hint-hand","dataset":"HInt: Hand Interactions in the wild","dataset_url":"/dataset/hint-hand-interactions-in-the-wild","rows_in_archive":10,"metrics":["PCK@0.05 (New Days) All","PCK@0.05 (VISOR) All","PCK@0.05 (Ego4D) All","PCK@0.05 (NewDays) Visible","PCK@0.05 (VISOR) Visible","PCK@0.05 (Ego4D) Visible","PCK@0.05 (NewDays) Occ","PCK@0.05 (VISOR) Occ","PCK@0.05 (Ego4D) Occ"],"first_row_in_archive_order":{"model":"ExtPose*","paper_title":"ExtPose: Robust and Coherent Pose Estimation by Extending ViTs","paper_url":"/paper/extpose-robust-and-coherent-pose-estimation","paper_date":"2025-06-18","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-hand-pose-estimation-on-ho-3d-v3","slug":"3d-hand-pose-estimation-on-ho-3d-v3","dataset":"HO-3D v3","dataset_url":"/dataset/ho-3d-v3","rows_in_archive":8,"metrics":["PA-MPJPE","PA-MPVPE","F@5mm","F@15mm","AUC_J","AUC_V"],"first_row_in_archive_order":{"model":"Hamba","paper_title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","paper_url":"/paper/hamba-single-view-3d-hand-reconstruction-with","paper_date":"2024-07-12","arxiv_id":"2407.09646","code_links":[{"title":"humansensinglab/Hamba","url":"https://github.com/humansensinglab/Hamba"}],"syntology":{"n":11,"n_ran":7,"n_unverified":4,"n_pointer_only":11}}},{"leaderboard":"/sota/3d-hand-pose-estimation-on-interhand2-6m","slug":"3d-hand-pose-estimation-on-interhand2-6m","dataset":"InterHand2.6M","dataset_url":"/dataset/interhand2-6m","rows_in_archive":1,"metrics":["MPJPE"],"first_row_in_archive_order":{"model":"Epipolar Transformers","paper_title":"Epipolar Transformers","paper_url":"/paper/epipolar-transformers","paper_date":"2020-05-10","arxiv_id":"2005.04551","code_links":[{"title":"yihui-he/epipolar-transformers","url":"https://github.com/yihui-he/epipolar-transformers"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/freihand","name":"FreiHAND","full_name":"FreiHAND","num_papers_in_archive":125},{"url":"/dataset/dexycb","name":"DexYCB","full_name":"","num_papers_in_archive":94},{"url":"/dataset/agora","name":"AGORA","full_name":"","num_papers_in_archive":68},{"url":"/dataset/interhand2-6m","name":"InterHand2.6M","full_name":"","num_papers_in_archive":50},{"url":"/dataset/ho-3d","name":"HO-3D v2","full_name":"","num_papers_in_archive":36},{"url":"/dataset/expose","name":"ExPose","full_name":"EXpressive POse and Shape rEgression","num_papers_in_archive":31},{"url":"/dataset/3d-hand-pose","name":"3D Hand Pose","full_name":"","num_papers_in_archive":16},{"url":"/dataset/first-person-hand-action-benchmark","name":"First-Person Hand Action Benchmark","full_name":"","num_papers_in_archive":15},{"url":"/dataset/h2o-dataset","name":"H2O  (2 Hands and Objects)","full_name":"","num_papers_in_archive":14},{"url":"/dataset/egodexter","name":"EgoDexter","full_name":"EgoDexter","num_papers_in_archive":13},{"url":"/dataset/ho-3d-v3","name":"HO-3D v3","full_name":"","num_papers_in_archive":10},{"url":"/dataset/h3wb","name":"H3WB","full_name":"Human 3.6M 3D WholeBody","num_papers_in_archive":8},{"url":"/dataset/hint-hand-interactions-in-the-wild","name":"HInt: Hand Interactions in the wild","full_name":"","num_papers_in_archive":8},{"url":"/dataset/synthhands","name":"SynthHands","full_name":"SynthHands","num_papers_in_archive":7},{"url":"/dataset/egopat3d","name":"EgoPAT3D","full_name":"","num_papers_in_archive":5},{"url":"/dataset/egopat3d-dt","name":"EgoPAT3D-DT","full_name":"EgoPAT3D-DT","num_papers_in_archive":3},{"url":"/dataset/icvl-hand-posture","name":"ICVL Hand Posture","full_name":"ICVL Hand Posture Dataset","num_papers_in_archive":3},{"url":"/dataset/muvihand","name":"MuViHand","full_name":"","num_papers_in_archive":2},{"url":"/dataset/thermohands","name":"ThermoHands","full_name":"","num_papers_in_archive":2},{"url":"/dataset/bighand2-2m-benchmark","name":"BigHand2.2M Benchmark","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/3d-canonical-hand-pose-estimation","name":"3D Canonical Hand Pose Estimation"},{"url":"/task/grasp-generation","name":"Grasp Generation"},{"url":"/task/hand-object-pose","name":"hand-object pose"}],"parent_tasks":[{"url":"/task/hand-pose-estimation","name":"Hand Pose Estimation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":87,"tagged_in_all":178,"items":[{"url":"/paper/end-to-end-recovery-of-human-shape-and-pose","title":"End-to-end Recovery of Human Shape and Pose","date":"2017-12-18","arxiv_id":"1712.06584","repositories_listed":10,"syntology":null},{"url":"/paper/learning-to-estimate-3d-hand-pose-from-single","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","date":"2017-05-03","arxiv_id":"1705.01389","repositories_listed":8,"syntology":null},{"url":"/paper/fastvit-a-fast-hybrid-vision-transformer","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","date":"2023-03-24","arxiv_id":"2303.14189","repositories_listed":6,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":5}},{"url":"/paper/v2v-posenet-voxel-to-voxel-prediction-network","title":"V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map","date":"2017-11-20","arxiv_id":"1711.07399","repositories_listed":5,"syntology":null},{"url":"/paper/weakly-supervised-mesh-convolutional-hand","title":"Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild","date":"2020-04-04","arxiv_id":"2004.01946","repositories_listed":4,"syntology":{"n":20,"n_ran":6,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/ho-3d-a-multi-user-multi-object-dataset-for","title":"HOnnotate: A method for 3D Annotation of Hand and Object Poses","date":"2019-07-02","arxiv_id":"1907.01481","repositories_listed":4,"syntology":null},{"url":"/paper/deepprior-improving-fast-and-accurate-3d-hand","title":"DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation","date":"2017-08-28","arxiv_id":"1708.08325","repositories_listed":4,"syntology":null},{"url":"/paper/mesh-graphormer","title":"Mesh Graphormer","date":"2021-04-01","arxiv_id":"2104.00272","repositories_listed":3,"syntology":null},{"url":"/paper/learning-joint-reconstruction-of-hands-and","title":"Learning joint reconstruction of hands and manipulated objects","date":"2019-04-11","arxiv_id":"1904.05767","repositories_listed":3,"syntology":null},{"url":"/paper/single-to-dual-view-adaptation-for-egocentric","title":"Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation","date":"2024-03-07","arxiv_id":"2403.04381","repositories_listed":2,"syntology":{"n":16,"n_ran":10,"n_unverified":6,"n_pointer_only":16}},{"url":"/paper/artiboost-boosting-articulated-3d-hand-object","title":"ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis","date":"2021-09-12","arxiv_id":"2109.05488","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-3d-hand-pose-estimation-from","title":"PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning","date":"2021-06-10","arxiv_id":"2106.05953","repositories_listed":2,"syntology":null},{"url":"/paper/dexycb-a-benchmark-for-capturing-hand","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","date":"2021-04-09","arxiv_id":"2104.04631","repositories_listed":2,"syntology":null},{"url":"/paper/handtailor-towards-high-precision-monocular","title":"HandTailor: Towards High-Precision Monocular 3D Hand Recovery","date":"2021-02-18","arxiv_id":"2102.09244","repositories_listed":2,"syntology":null},{"url":"/paper/interhand2-6m-a-dataset-and-baseline-for-3d","title":"InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image","date":"2020-08-21","arxiv_id":"2008.09309","repositories_listed":2,"syntology":null},{"url":"/paper/pose2mesh-graph-convolutional-network-for-3d","title":"Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose","date":"2020-08-20","arxiv_id":"2008.09047","repositories_listed":2,"syntology":null},{"url":"/paper/convolutional-mesh-regression-for-single","title":"Convolutional Mesh Regression for Single-Image Human Shape Reconstruction","date":"2019-05-08","arxiv_id":"1905.03244","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/3d-hand-shape-and-pose-estimation-from-a","title":"3D Hand Shape and Pose Estimation from a Single RGB Image","date":"2019-03-03","arxiv_id":"1903.00812","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-hand-mesh-recovery-from-a","title":"End-to-end Hand Mesh Recovery from a Monocular RGB Image","date":"2019-02-25","arxiv_id":"1902.09305","repositories_listed":2,"syntology":null},{"url":"/paper/3d-hand-shape-and-pose-from-images-in-the","title":"3D Hand Shape and Pose from Images in the Wild","date":"2019-02-09","arxiv_id":"1902.03451","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/monocular-3d-hand-pose-estimation-with","title":"Monocular 3D Hand Pose Estimation with Implicit Camera Alignment","date":"2025-06-10","arxiv_id":"2506.11133","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-the-synthetic-to-real-domain-gap-in","title":"Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation","date":"2025-03-25","arxiv_id":"2503.19307","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":6}},{"url":"/paper/simhand-mining-similar-hands-for-large-scale","title":"SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training","date":"2025-02-21","arxiv_id":"2502.15251","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/wilor-end-to-end-3d-hand-localization-and","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","date":"2024-09-18","arxiv_id":"2409.12259","repositories_listed":1,"syntology":null},{"url":"/paper/sharp-segmentation-of-hands-and-arms-by-range","title":"SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action Recognition","date":"2024-08-19","arxiv_id":"2408.10037","repositories_listed":1,"syntology":null},{"url":"/paper/handdagt-a-denoising-adaptive-graph","title":"HandDAGT: A Denoising Adaptive Graph Transformer for 3D Hand Pose Estimation","date":"2024-07-30","arxiv_id":"2407.20542","repositories_listed":1,"syntology":null},{"url":"/paper/attentionhand-text-driven-controllable-hand","title":"AttentionHand: Text-driven Controllable Hand Image Generation for 3D Hand Reconstruction in the Wild","date":"2024-07-25","arxiv_id":"2407.18034","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/hamba-single-view-3d-hand-reconstruction-with","title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","date":"2024-07-12","arxiv_id":"2407.09646","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_unverified":4,"n_pointer_only":11}},{"url":"/paper/handdiff-3d-hand-pose-estimation-with","title":"HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud","date":"2024-04-04","arxiv_id":"2404.03159","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/handbooster-boosting-3d-hand-mesh","title":"HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions","date":"2024-03-27","arxiv_id":"2403.18575","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_unverified":0,"n_pointer_only":0}}],"syntology_records":11,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}