Research map / 3D vision / Face and shape
Learned Binary Spectral Shape Descriptor for 3D Shape Correspondence
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 |
|---|---|---|---|
| learn a nonlinear binary spectral descriptor with the metric network | 3D shape correspondence · SCAPE | hit rate | Helped |
| learn a nonlinear binary spectral descriptor with the metric network | 3D shape correspondence · TOSCA | hit rate | Helped |
| use LBSSD instead of HKS-LSH | 3D shape correspondence · sampled pair of human shapes | correctly matching points: 8 -> 28 | Helped |
| use LBSSD instead of WKS-LSH | 3D shape correspondence · sampled pair of human shapes | correctly matching points: 5 -> 28 | Helped |
| use LBSSD instead of OSSD-LSH | 3D shape correspondence · sampled pair of human shapes | correctly matching points: 11 -> 28 | Helped |
| use LBSSD instead of OSSD-LSH | descriptor formation · SCAPE | time: 9.75s -> 8.75s | Helped |
| use LBSSD instead of HKS-LSH | descriptor formation · SCAPE | time: 8.13s -> 8.75s | Hurt |
| use LBSSD instead of WKS-LSH | descriptor formation · SCAPE | time: 8.13s -> 8.75s | Hurt |
Closest papers by meaning
- A Robust Local Spectral Descriptor for Matching Non-Rigid Shapes With Incompatible Shape Structures (CVPR 2019 · similarity 0.90)
- Shape correspondence using anisotropic Chebyshev spectral CNNs (CVPR 2020 · similarity 0.87)
- From Feature Learning to Spectral Basis Learning: A Unifying and Flexible Framework for Efficient and Robust Shape Matching (CVPR 2026 · similarity 0.86)
- Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation (CVPR 2024 · similarity 0.84)
- ShapeEmbed: a self-supervised learning framework for 2D contour quantification (NeurIPS 2025 · similarity 0.84)
- Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform (CVPR 2024 · similarity 0.82)
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.