Research map / 3D vision / Face and shape
Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction
Zhiying Leng, Shun-Cheng Wu, Mahdi Saleh, Antonio Montanaro, Hao Yu, Yin Wang, Nassir Navab, Xiaohui Liang, Federico Tombari
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 dynamic hyperbolic graph convolution (DHGC) to baseline (ablation) | Hasson et al. baseline · Obman | hand error (mm): 11.6 -> 10.9 | Improved |
| add image-attention hyperbolic graph convolution (IHGC) on top of DHGC (ablation) | DHANet · Obman | object error (mm): 582.9 -> 529.3 | Improved |
| hyperbolic instead of Euclidean space for both modules (ablation) | DHANet · Obman | object error (mm): 586.1 -> 529.3 | Improved |
| hyperbolic instead of Euclidean space for both modules (ablation) | DHANet · Obman | hand error (mm): 11.1 -> 10.2 | Improved |
| Euclidean DHGC alone on baseline (ablation) | Hasson et al. baseline · Obman | max penetration (mm): 9.5 -> 10.8 | Hurt |
| DHANet vs Hasson baseline on Obman | hand-object reconstruction · Obman | object error (mm): 641.5 -> 529.3 | Improved |
| non-iterative DHANet vs dual-iterative Tse et al. | hand-object reconstruction · Obman | hand error (mm): 9.1 -> 10.2 | Hurt |
| DHANet vs Tse et al. on real-image FHB- | hand-object reconstruction · FHB- | hand error (mm): 25.3 -> 23.8 | Improved |
| DHANet vs Cao et al. on HO-3D | hand-object reconstruction · HO-3D v2 | hand error (mm): 9.7 -> 6.1 | Improved |
Closest papers by meaning
- Collaborative Learning for Hand and Object Reconstruction With Attention-Guided Graph Convolution (CVPR 2022 · similarity 0.89)
- Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering (AAAI 2024 · similarity 0.87)
- Learning Explicit Contact for Implicit Reconstruction of Hand-Held Objects from Monocular Images (AAAI 2024 · similarity 0.86)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · similarity 0.86)
- SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation (AAAI 2024 · similarity 0.86)
- SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit Meshes (NeurIPS 2025 · 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.
