{"url":"/dataset/ho-3d-v3","name":"HO-3D v3","full_name":null,"description_markdown":"The HO-3D v3 is the version 3 of the HO-3D dataset with more accurate hand-object poses. HO-3D v3 provides more accurate annotations for both the hand and object poses thus resulting in better estimates of contact regions between the hand and the object. The table below shows the statistics of the HO-3D v2 compared to the HO-3D v3 datasets.\r\n\r\n| Dataset   | Train Set | Test Set | #Images | #Objects | #Subjects | Release Date |\r\n|-----------|-----------|----------|---------|----------|-----------|--------------|\r\n| HO-3D v2  | 66,034    | 11,524   | 10      | 10       | 9         | 9 Jan 2020   |\r\n| HO-3D v3  | 83,325    | 20,137   | 10      | 10       | 1         | 1 Jul 2021   |\r\n\r\nSource: [Official Dataset](https://codalab.lisn.upsaclay.fr/competitions/4393)\r\nImage Source: [Official Dataset](https://arxiv.org/abs/2107.00887)","description_withheld":null,"homepage":"https://www.tugraz.at/index.php?id=40231","introduced_date":"2021-07-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/ho-3d-v3-improving-the-accuracy-of-hand","title":"HO-3D_v3: Improving the Accuracy of Hand-Object Annotations of the HO-3D Dataset","first_author":"Shreyas Hampali","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"3D Hand Pose Estimation","url":"/task/3d-hand-pose-estimation","datasets_with_task":"/datasets/task/3d-hand-pose-estimation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["HO-3D v3"],"data_loaders":[],"num_papers_in_archive":10,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-hand-pose-estimation-on-ho-3d-v3","task":"3D Hand Pose Estimation","dataset_variant":"HO-3D v3","rows":8,"metrics":["PA-MPJPE","PA-MPVPE","F@5mm","F@15mm","AUC_J","AUC_V"],"first_row_in_archive_order":{"model":"Hamba","paper":"/paper/hamba-single-view-3d-hand-reconstruction-with","metrics":{"AUC_J":"0.861","AUC_V":"0.864","F@15mm":"0.982","F@5mm":"0.681","PA-MPJPE":"6.9","PA-MPVPE":"6.8"},"code_links":[{"title":"humansensinglab/Hamba","url":"https://github.com/humansensinglab/Hamba"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mmhmr-generative-masked-modeling-for-hand","title":"MMHMR: Generative Masked Modeling for Hand Mesh Recovery","date":"2024-12-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":7,"samples_unverified":4,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hmp-hand-motion-priors-for-pose-and-shape","title":"HMP: Hand Motion Priors for Pose and Shape Estimation from Video","date":"2023-12-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-probabilistic-attention-model-with","title":"A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Image","date":"2023-04-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/uv-based-3d-hand-object-reconstruction-with","title":"UV-Based 3D Hand-Object Reconstruction with Grasp Optimization","date":"2022-11-24","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/handsformer-keypoint-transformer-for","title":"Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation","date":"2021-04-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/model-based-3d-hand-reconstruction-via-self","title":"Model-based 3D Hand Reconstruction via Self-Supervised Learning","date":"2021-03-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":4,"samples_unverified":3,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":18,"samples_ran":11,"samples_unverified":7,"pointer_only_for_licence":18,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}