Research map / 3D vision / Face and shape
LISA: Learning Implicit Shape and Appearance of Hands
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 |
|---|---|---|---|
| Use per-bone SDF and color predictions blended by learned skinning weights | LISA · 3DH and MANO point-cloud tests | V2V [mm]: 3.05 -> 2.93; 3.14 -> 3.09 | Helped |
| Add the geometric prior to image training (ablation) | LISA-im · 3DH and MANO point-cloud tests, reconstruction to scan | V2V [mm]: 2.93 -> 1.93; 3.09 -> 1.45 | Helped |
| Train only with the geometric prior instead of images (ablation) | LISA · 3DH and MANO point-cloud tests, reconstruction to scan | V2V [mm]: 2.93 -> 0.83; 3.09 -> 0.36 | Helped |
| Add the geometric prior to image training (ablation) | LISA-im · DeepHandMesh, 1 view | V2V: 5.48 -> 3.84 | Helped |
| Add the geometric prior to image training (ablation) | LISA-im · DeepHandMesh, 2 and 4 views | V2V: 3.86 -> 3.70; 3.62 -> 3.53 | Helped |
| Add the geometric prior to image training (ablation) | LISA-im · DeepHandMesh, 1 view | PSNR: 25.04 -> 25.43 | Helped |
| Add the geometric prior to image training (ablation) | LISA-im · InterHand2.6M color reconstruction, 1 view | LPIPS: 0.08 -> 0.06 | Helped |
| Add the geometric prior to image training (ablation) | LISA-im · InterHand2.6M color reconstruction, 2 views | LPIPS: 0.07 -> 0.06 | Helped |
| Add the geometric prior to image training (ablation) | LISA-im · InterHand2.6M color reconstruction, 4 views | LPIPS: 0.07 -> 0.05 | Helped |
| Use images and geometric prior together rather than the geometric prior alone (ablation) | LISA-geom · 3DH point-cloud test, reconstruction to scan | V2V [mm]: 0.83 -> 1.93 | Hurt |
| Use images and geometric prior together rather than the geometric prior alone (ablation) | LISA-geom · MANO point-cloud test, reconstruction to scan | V2V [mm]: 0.36 -> 1.45 | Hurt |
| Use the geometric prior in image reconstruction (ablation) | LISA-im · DeepHandMesh novel-view color reconstruction | PSNR: 1 view: 25.04 -> 25.43; 2 views: 29.84 -> 29.40; 4 views: 30.21 -> 29.69 | Mixed |
Closest papers by meaning
- 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)
- FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation (CVPR 2025 · similarity 0.88)
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · similarity 0.88)
- Learning Explicit Contact for Implicit Reconstruction of Hand-Held Objects from Monocular Images (AAAI 2024 · similarity 0.87)
- HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances (CVPR 2024 · similarity 0.87)
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.