Research map / 3D vision / Face and shape
Smooth Shells: Multi-Scale Shape Registration With Functional Maps
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 |
|---|---|---|---|
| Add feature regularization (ablation) | Smooth Shells · SCAPE | Avg. error: 0.0211 -> 0.0088 | Helped |
| Add feature regularization (ablation) | Smooth Shells · TOSCA | Avg. error: 0.0075 -> 0.0056 | Helped |
| Add ARAP regularization (ablation) | Smooth Shells · SCAPE | Avg. error: 0.0147 -> 0.0088 | Helped |
| Add ARAP regularization (ablation) | Smooth Shells · TOSCA | Avg. Distortion: 0.1926 -> 0.1654 | Helped |
| Combine intrinsic and extrinsic embeddings rather than using extrinsic only (ablation) | Smooth Shells · SCAPE | Avg. error: 0.0344 -> 0.0088 | Helped |
| Combine intrinsic and extrinsic embeddings rather than using intrinsic only (ablation) | Smooth Shells · TOSCA | Avg. error: 0.0205 -> 0.0056 | Helped |
| Include normals in the embedding (ablation) | Smooth Shells · SCAPE | Avg. error: 0.0115 -> 0.0088 | Helped |
| Use MCMC initialization (ablation) | Smooth Shells · SCAPE | % Failure: 0.8310 -> 0 | Helped |
| Use MCMC initialization (ablation) | Smooth Shells · TOSCA | Avg. error: 0.1039 -> 0.0056 | Helped |
| Use MCMC initialization instead of random rigid poses (ablation) | Smooth Shells · TOSCA | Avg. error: 0.0694 -> 0.0056 | Helped |
| Use smooth shells rather than spectral reconstruction (ablation) | Smooth Shells · SCAPE | Avg. error: 0.0139 -> 0.0088 | Helped |
| Use smooth shells rather than spectral reconstruction (ablation) | Smooth Shells · TOSCA | Avg. error: 0.0098 -> 0.0056 | Helped |
Closest papers by meaning
- Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation (CVPR 2024 · similarity 0.87)
- Denoising Functional Maps: Diffusion Models for Shape Correspondence (CVPR 2025 · similarity 0.87)
- Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondence (CVPR 2025 · similarity 0.87)
- Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching (CVPR 2024 · similarity 0.86)
- Multi-Shape Matching with Cycle Consistency Basis via Functional Maps (AAAI 2025 · similarity 0.86)
- Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learning (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.