Datasets › H3WB
H3WB (Human 3.6M 3D WholeBody)
Human3.6M 3D WholeBody (H3WB) is a large scale dataset with 133 whole-body keypoint annotations on 100K images, made possible by a new multi-view pipeline. It is designed for the three new tasks : i) 3D whole-body pose lifting from 2D complete whole-body pose, ii) 3D whole-body pose lifting from 2D incomplete whole-body pose, iii) 3D whole-body pose estimation from a single RGB image.
Source: H3WB: Human3.6M 3D WholeBody Dataset and Benchmark
Image Source: https://arxiv.org/pdf/2211.15692v1.pdf
Benchmarks archive 2025-07-28
All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| 3D Human Pose Estimation | H3WB | SemGAN MPJPE 45.39 | 3D WholeBody Pose Estimation based on Semantic Graph... | — | 17 | Compare |
| 3D Facial Landmark Localization | H3WB | 3D-LFM Average MPJPE (mm) 10.44 | 3D-LFM: Lifting Foundation Model | mosamdabhi/3dlfm | 15 | Compare |
| 3D Hand Pose Estimation | H3WB | SemGAN Average MPJPE (mm) 27.77 | 3D WholeBody Pose Estimation based on Semantic Graph... | — | 15 | Compare |
Papers archive 2025-07-28
5 shown of 5 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 8. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation | 1 | 1 | 11 Jul 2024 | not harvested |
| 3D WholeBody Pose Estimation based on Semantic Graph Attention Network and Distance Information | 0 | 3 | 3 Jun 2024 | not harvested |
| 3D-LFM: Lifting Foundation Model | 1 | 3 | 19 Dec 2023 | not harvested |
| H3WB: Human3.6M 3D WholeBody Dataset and Benchmark | 1 | 39 | 28 Nov 2022 | not harvested |
| Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation | 1 | 1 | 7 Aug 2022 | not harvested |
Dataset loaders archive 2025-07-28
1 loader as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- H3WB
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections