Research map / 3D vision / Face and shape
MeMaHand: Exploiting Mesh-Mano Interaction for Single Image Two-Hand Reconstruction
Congyi Wang, Feida Zhu, Shilei Wen
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 |
|---|---|---|---|
| combine mesh vertices and MANO parameter predictions through mesh-MANO interaction | MeMaHand · InterHand2.6M interacting hands test | MPJPE (mm): 8.79 -> 8.65 | Improved |
| combine mesh vertices and MANO parameter predictions through mesh-MANO interaction | MeMaHand · InterHand2.6M interacting hands test, MANO mesh evaluation | MPJPE (mm): 13.48 -> 10.85 | Improved |
| add MANO tokens to the mesh-MANO interaction module (ablation) | MeMaHand · InterHand2.6M interacting hands test | MPJPE (mm): 8.87 -> 8.65 | Improved |
| add mesh alignment refinement (ablation) | MeMaHand · InterHand2.6M interacting hands test | MPJPE (mm): 8.79 -> 8.65 | Improved |
| use multi-scale rather than single-scale mesh-aligned image features (ablation) | MeMaHand · InterHand2.6M interacting hands test | MPJPE (mm): 8.73 -> 8.65; 8.77 -> 8.65 | Improved |
| update MANO parameters through MMIB rather than regressing them from F_gap (ablation) | MeMaHand · InterHand2.6M interacting hands test | MPJPE (mm): 8.83 -> 8.65 | Improved |
| use asymmetric attention masks (ablation) | MeMaHand · InterHand2.6M interacting hands test | MPJPE (mm): 9.17 -> 8.65 | Improved |
| pretrain the image encoder-decoder on auxiliary hand tasks instead of ImageNet (ablation) | MeMaHand · InterHand2.6M interacting hands test | MPJPE (mm): 9.11 -> 8.65 | Improved |
Closest papers by meaning
- HandOS: 3D Hand Reconstruction in One Stage (CVPR 2025 · similarity 0.89)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · similarity 0.88)
- Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering (AAAI 2024 · similarity 0.88)
- SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation (AAAI 2024 · similarity 0.88)
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · similarity 0.88)
- BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting (CVPR 2025 · similarity 0.88)
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.
