| ExtPose: Robust and Coherent Pose Estimation by Extending ViTs | | 6.9 | 7.3 | 0.667 | 0.991 | 0.863 | 0.856 | ExtPose (T=16) | 2025-06-18 |
| Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba | ✓ Link | 7.5 | 7.7 | 0.648 | 0.982 | 0.850 | 0.846 | Hamba | 2024-07-12 |
| WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild | ✓ Link | 7.5 | 7.7 | 0.646 | 0.983 | 0.851 | 0.846 | WiLoR | 2024-09-18 |
| Reconstructing Hands in 3D with Transformers | ✓ Link | 7.7 | 7.9 | 0.635 | 0.980 | 0.846 | 0.841 | HaMeR | 2023-12-08 |
| HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions | ✓ Link | 8.2 | 8.4 | 0.585 | 0.972 | 0.836 | 0.832 | HandBooster | 2024-03-27 |
| A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Image | ✓ Link | 8.3 | 8.2 | 0.608 | 0.965 | 0.835 | 0.836 | AMVUR | 2023-04-27 |
| H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction | ✓ Link | 8.5 | 8.6 | 0.570 | 0.966 | 0.829 | 0.828 | H2ONet | 2023-01-01 |
| 3D Hand Reconstruction via Aggregating Intra and Inter Graphs Guided by Prior Knowledge for Hand-Object Interaction Scenario | | 8.8 | | | | | | SemGCN | 2024-03-04 |
| Harmonious Feature Learning for Interactive Hand-Object Pose Estimation | ✓ Link | 8.9 | 8.7 | 0.575 | 0.965 | | | HFL-Net | 2023-01-01 |
| HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network | | 9.1 | 8.8 | 0.564 | 0.963 | 0.819 | 0.819 | HandOccNet | 2022-03-28 |
| MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image | ✓ Link | 9.2 | 9.4 | 0.538 | 0.957 | | | MobRecon | 2021-12-06 |
| HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields | ✓ Link | 9.2 | | | | | | HOISDF | 2024-02-26 |
| I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modeling | | 9.9 | 10.1 | 0.500 | 0.943 | 0.804 | 0.799 | I2UV-HandNet | 2021-02-07 |
| Interacting Hand-Object Pose Estimation via Dense Mutual Attention | ✓ Link | 10.1 | | | | | | DMA | 2022-11-16 |
| Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time | ✓ Link | 10.1 | | | | | | SHO | 2021-06-09 |
| End-to-End Human Pose and Mesh Reconstruction with Transformers | ✓ Link | 10.4 | 11.1 | 0.484 | 0.946 | 0.792 | 0.779 | METRO | 2020-12-17 |
| HOnnotate: A method for 3D Annotation of Hand and Object Poses | ✓ Link | 10.7 | 10.6 | 0.506 | 0.942 | 0.788 | 0.790 | Hampali et al. | 2019-07-02 |
| Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation | ✓ Link | 10.8 | | | | 0.786 | | KPT-Transformer | 2021-04-29 |
| I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image | ✓ Link | 11.2 | 13.9 | 0.409 | 0.932 | 0.775 | 0.722 | I2L-MeshNet | 2020-08-09 |
| ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis | ✓ Link | 11.4 | 10.9 | 0.488 | 0.944 | 0.773 | 0.782 | ArtiBoost | 2021-09-12 |
| Model-based 3D Hand Reconstruction via Self-Supervised Learning | ✓ Link | 11.4 | 11.2 | 0.450 | 0.930 | 0.773 | 0.777 | S2Hand | 2021-03-22 |
| Towards unconstrained joint hand-object reconstruction from RGB videos | ✓ Link | 12.0 | | | | | | HOR | 2021-08-16 |
| Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose | ✓ Link | 12.5 | 12.7 | 0.441 | 0.909 | 0.754 | 0.749 | Pose2Mesh | 2020-08-20 |
| Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution | | | 10.9 | 0.485 | 0.943 | | | Tse et al. | 2022-04-27 |