Research map / Learning theory and algorithms / Matrix and tensor methods
Geodesic Distance Descriptors
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 GDD instead of functional maps for shape correspondence | GDD · TOSCA and SCAPE | correspondence accuracy | Helped |
| Use GDD instead of SGMDS with the same initialization | GDD · TOSCA and SCAPE | correspondence accuracy | Helped |
| Add LBO-basis ICP post-processing after GDD correspondence (ablation) | GDD-5pt · TOSCA and SCAPE | correspondence accuracy | Helped |
| Add LBO-basis ICP post-processing after GDD correspondence (ablation) | GDD-5pt · GH-related minimizer approximation | distortion | Hurt |
| Use GDD-5pt rather than LBO eigenfunctions (Phi-5pt) (ablation) | 5-point-initialized ICP · TOSCA and SCAPE | correspondence accuracy | Helped |
| Refine SGMDS correspondences with GDD | SGMDS · TOSCA and SCAPE | correspondence accuracy | Helped |
| Refine functional-map correspondences with GDD | functional maps · TOSCA and SCAPE | correspondence accuracy | Helped |
| Refine Spectral-GF correspondences with GDD | Spectral-GF · TOSCA and SCAPE | correspondence accuracy | Helped |
| Use approximate geodesic-distance basis instead of the exact basis (ablation) | GDD · Wolf (TOSCA) | geodesic-distance reconstruction error | No clear effect |
Closest papers by meaning
- Wormhole Loss for Partial Shape Matching (NeurIPS 2024 · similarity 0.88)
- Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching (CVPR 2024 · similarity 0.84)
- Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation (CVPR 2024 · similarity 0.84)
- Partial Gromov-Wasserstein Metric (ICLR 2025 · similarity 0.83)
- Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformation (CVPR 2025 · similarity 0.83)
- Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models (NeurIPS 2025 · similarity 0.83)
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.