Research map / 3D vision / 3D generation
ACR: Attention Collaboration-Based Regressor for Arbitrary Two-Hand Reconstruction
Read the paperCheck 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 |
|---|---|---|---|
| use ACR instead of IntagHand | two-hand reconstruction · InterHand2.6M IH test | MPJPE: 10.27 -> 9.08 | Helped |
| use ACR instead of IntagHand | two-hand reconstruction · InterHand2.6M test | MPJPE: 9.95 -> 8.09 | Helped |
| use ACR instead of Mesh Graphormer | hand reconstruction · FreiHand | PA-MPJPE: 6 -> 6.9 | Hurt |
| add part-based representation to global representation (ablation) | ACR · InterHand2.6M ablation | MPJPE: 9.56 -> 8.52 | Helped |
| add cross-hand prior to global representation (ablation) | ACR · InterHand2.6M ablation | MPJPE: 9.56 -> 9.1 | Helped |
| add both part-based representation and cross-hand prior (ablation) | ACR · InterHand2.6M IH ablation | MPJPE: 10.35 -> 9.08 | Helped |
| add cross-hand prior to global representation (ablation) | ACR · InterHand2.6M IH ablation | MPJPE: 10.35 -> 9.88 | Helped |
| add part-based representation to global representation (ablation) | ACR · InterHand2.6M IH ablation | MPJPE: 10.35 -> 9.69 | Helped |
| use HRNet-32W rather than ResNet-50 for the global-only model (ablation) | ACR global representation · InterHand2.6M ablation | MPJPE: 9.78 -> 9.56 | Helped |
| use ACR instead of IntagHand | hand reconstruction · InterHand2.6M SH test | MPJPE: 9.67 -> 6.85 | Helped |
Closest papers by meaning
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · similarity 0.89)
- BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting (CVPR 2025 · similarity 0.88)
- EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild (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 0.88)
- Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering (AAAI 2024 · similarity 0.88)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · 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.