Research map / 3D vision / Face and shape
Efficient Globally Optimal 2D-To-3D Deformable Shape Matching
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 globally optimized continuous matching for retrieval | Ours · TOSCA | MAP: 0.2489 -> 0.9012 | Helped |
| Use globally optimized continuous matching for retrieval | Ours · TOSCA | MAP: 0.2369 -> 0.9012 | Helped |
| Use globally optimized continuous matching for retrieval | Ours · TOSCA horse | AP: 0.0611 -> 0.5062; 0.0629 -> 0.5062 | Mixed |
| Use globally optimized continuous matching for retrieval | Ours · TOSCA human | AP: 0.9078 -> 1.0000 | Mixed |
| Add the segment feature to the matching framework (ablation) | Ours · FAUST | runtime: 2–3 orders of magnitude | Helped |
| Increase spectral eigenfunction count beyond 25 (ablation) | Ours · FAUST subset | matching error | Hurt |
Closest papers by meaning
- SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency (CVPR 2024 · similarity 0.90)
- Partial-to-Partial Shape Matching with Geometric Consistency (CVPR 2024 · similarity 0.86)
- HOPE: Shape Matching Via Aligning Different K-hop Neighbourhoods (NeurIPS 2024 · similarity 0.85)
- KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation (CVPR 2024 · similarity 0.85)
- 3D Geometric Shape Assembly via Efficient Point Cloud Matching (ICML 2024 · similarity 0.84)
- EchoMatch: Partial-to-Partial Shape Matching via Correspondence Reflection (CVPR 2025 · similarity 0.84)
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.