Research map / Graph learning / Knowledge and temporal graphs
Interacting Attention Graph for Single Image Two-Hand Reconstruction
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 CHA to the two-hand GCN (ablation) | IntagHand · InterHand2.6M | MPJPE: 9.97 -> 9.34 | Helped |
| Add CHA to the two-hand GCN (ablation) | IntagHand · InterHand2.6M | MPVPE: 10.63 -> 9.59 | Helped |
| Add image feature attention using 32×32 features consistently (ablation) | GCN + CHA · InterHand2.6M | MPJPE: 9.34 -> 8.90 | Helped |
| Add image feature attention using 32×32 features consistently (ablation) | GCN + CHA · InterHand2.6M | MPVPE: 9.59 -> 9.16 | Helped |
| Add image feature attention using 8×8 features consistently (ablation) | GCN + CHA · InterHand2.6M | MPJPE: 9.34 -> 8.83 | Helped |
| Add image feature attention using 8×8 features consistently (ablation) | GCN + CHA · InterHand2.6M | MPVPE: 9.59 -> 9.07 | Helped |
| Use pyramid image features instead of consistent 32×32 features (ablation) | GCN + CHA + image feature attention · InterHand2.6M | MPJPE: 8.90 -> 8.79 | Helped |
| Use pyramid image features instead of consistent 32×32 features (ablation) | GCN + CHA + image feature attention · InterHand2.6M | MPVPE: 9.16 -> 9.03 | Helped |
| Use pyramid image features instead of consistent 8×8 features (ablation) | GCN + CHA + image feature attention · InterHand2.6M | MPJPE: 8.83 -> 8.79 | Helped |
| Use pyramid image features instead of consistent 8×8 features (ablation) | GCN + CHA + image feature attention · InterHand2.6M | MPVPE: 9.07 -> 9.03 | Helped |
| Replace Zhang et al. with IntagHand | Two-hand reconstruction · InterHand2.6M | MPJPE: 13.48 -> 8.79 | Helped |
| Replace Zhang et al. with IntagHand | Two-hand reconstruction · InterHand2.6M | MPVPE: 13.95 -> 9.03 | Helped |
Closest papers by meaning
- Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering (AAAI 2024 · similarity 0.89)
- BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting (CVPR 2025 · similarity 0.88)
- SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit Meshes (NeurIPS 2025 · similarity 0.87)
- BiTT: Bi-directional Texture Reconstruction of Interacting Two Hands from a Single Image (CVPR 2024 · similarity 0.86)
- Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba (NeurIPS 2024 · similarity 0.86)
- SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation (AAAI 2024 · similarity 0.86)
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.