Research map / 3D vision / Face and shape
PHRIT: Parametric Hand Representation with Implicit Template
Zhisheng Huang, Yujin Chen, Di Kang, Jinlu Zhang, Zhigang Tu
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 E_norm loss from the deformation field (ablation) | PHRIT · MANO test set (recon to scan) | V2V: 0.51 -> 0.37 | Improved |
| add deformation skip connections (ablation) | PHRIT · MANO test set (recon to scan) | V2V: 0.47 -> 0.37 | Improved |
| replace E_mano+ pseudo dense supervision with implicit deformation-field correspondence (ablation) | PHRIT · MANO test set (recon to scan) | V2V: 0.45 -> 0.37 | Improved |
| use PHRIT instead of HALO | skeleton-driven reconstruction · YT3D | Chamfer-L1: 0.719 -> 0.432 | Improved |
| use PHRIT instead of MANO | point-cloud reconstruction · MANO test set | V2V recon to scan: 3.14 -> 0.37 | Improved |
| use PHRIT instead of LISA-full trained on 13k private scans | point-cloud reconstruction · MANO test set | V2V recon to scan: 1.45 -> 0.37 | Improved |
| use PHRIT instead of LISA-geom | point-cloud reconstruction · MANO test set | V2V recon to scan: 0.36 -> 0.37 | No clear effect |
| use PHRIT instead of DHM | single-view reconstruction · DHM public subset | M_err: 1.98 -> 1.50 | Improved |
| use Ours-low instead of MANO in I2L-MeshNet | FreiHAND · FreiHAND | MPVPE: 12.4 -> 7.8 | Improved |
| use looser chamfer supervision with high-res template (Ours-high) instead of per-vertex low-res | PHRIT · FreiHAND | MPVPE: 7.8 -> 8.0 | Hurt |
| use PHRIT instead of MANO for inference speed | feed-forward reconstruction · inference time | speed (s): 0.003 -> 0.099 | Hurt |
| use PHRIT instead of HALO for inference speed | feed-forward reconstruction · inference time | speed (s): 16.3 -> 0.099 | Improved |
Closest papers by meaning
- HTML: A Parametric Hand Texture Model for 3D Hand Reconstruction and Personalization (ECCV 2020 · similarity 0.90)
- SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit Meshes (NeurIPS 2025 · similarity 0.87)
- Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering (AAAI 2024 · similarity 0.86)
- HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances (CVPR 2024 · similarity 0.86)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · similarity 0.85)
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · similarity 0.85)
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.
