Research map / 3D vision / Face and shape
A Robust Local Spectral Descriptor for Matching Non-Rigid Shapes With Incompatible Shape Structures
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 the learned LPS-based descriptor instead of LDGI | FAUST matching at the original resolution · FAUST | matching performance | Helped |
| Train on original-resolution shapes and test on different resolutions | LPS-based descriptor · FAUST-derived multi-resolution shapes | matching performance | No clear effect |
| Use the learned LPS-based descriptor rather than the compared descriptors | Dense matching across resolutions · FAUST 6890-to-8K and 6890-to-12K | matching performance | Helped |
| Use the learned LPS-based descriptor rather than the compared descriptors | Matching randomly rotated shapes · FAUST-derived rotated shapes | matching performance | Helped |
| Use the learned LPS-based descriptor rather than the compared descriptors | Matching randomly scaled shapes · FAUST-derived scaled shapes | matching performance | Helped |
| Replace GCNN's SHOT input feature with LPS | GCNN shape correspondence · FAUST | correspondence quality | Mixed |
Closest papers by meaning
- Learned Binary Spectral Shape Descriptor for 3D Shape Correspondence (CVPR 2016 · similarity 0.90)
- From Feature Learning to Spectral Basis Learning: A Unifying and Flexible Framework for Efficient and Robust Shape Matching (CVPR 2026 · similarity 0.88)
- Unsupervised Contrastive Learning for Efficient and Robust Spectral Shape Matching (AAAI 2026 · similarity 0.87)
- Medial Spectral Coordinates for 3D Shape Analysis (CVPR 2022 · similarity 0.87)
- Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation (CVPR 2024 · similarity 0.86)
- HOPE: Shape Matching Via Aligning Different K-hop Neighbourhoods (NeurIPS 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.