Research map / 3D vision / Human pose estimation
Interacting Two-Hand 3D Pose and Shape Reconstruction From Single Color Image
Baowen Zhang, Yangang Wang, Xiaoming Deng, Yinda Zhang, Ping Tan, Cuixia Ma, Hongan Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add context-aware refinement with both hands' MANO parameters instead of single hand (ablation) | Ours · InterHand2.6M | MPJPE: 13.170 -> 13.071 | Improved |
| add context-aware refinement with both hands' MANO parameters instead of single hand (ablation) | Ours · InterHand2.6M | AUC(0-50mm): 0.752 -> 0.754 | Improved |
| use multi-scale encoder features instead of high-level feature only (ablation) | Ours · InterHand2.6M | MPJPE: 13.986 -> 13.071 | Improved |
| add attention module in cascaded refinement (ablation) | Ours · InterHand2.6M | MPJPE: 14.095 -> 13.071 | Improved |
| generate attention from rendered predicted joints instead of predicted 2.5D heatmap (ablation) | Ours · InterHand2.6M | MPJPE: 13.464 -> 13.071 | Improved |
| fit camera parameters by alignment instead of network-predicted camera (ablation) | Ours · InterHand2.6M | MPJPE: 14.040 -> 13.071 | Improved |
| add cascaded blocks and attention modules to baseline network (ablation) | Ours · InterHand2.6M | MPJPE: 14.218 -> 13.071 | Improved |
| two-hand model versus best single-hand method (Spurr et al.) | Ours · InterHand2.6M | MPJPE: 15.402 -> 13.071 | Improved |
| two-hand model versus Moon et al. InterHand | Ours · InterHand2.6M | MPJPE: 16.888 -> 13.071 | Improved |
| two-hand model versus Zhou et al. on shape | Ours · InterHand2.6M | shape-err: 23.892 -> 10.398 | Improved |
| two-hand model versus Zhou et al. on Haggling | Ours · Haggling | MPJPE: 13.203 -> 11.419 | Improved |
Closest papers by meaning
- Collaborative Learning for Hand and Object Reconstruction With Attention-Guided Graph Convolution (CVPR 2022 · similarity 0.91)
- 3D Hand Shape and Pose Estimation From a Single RGB Image (CVPR 2019 · similarity 0.91)
- Interacting Attention Graph for Single Image Two-Hand Reconstruction (CVPR 2022 · similarity 0.91)
- 3D Hand Shape and Pose From Images in the Wild (CVPR 2019 · similarity 0.91)
- Model-Based 3D Hand Reconstruction via Self-Supervised Learning (CVPR 2021 · similarity 0.90)
- End-to-End Detection and Pose Estimation of Two Interacting Hands (ICCV 2021 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
