Research map / Point clouds / Point cloud classification
Correspondence learning via linearly-invariant embedding
Read the paperCheck 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 a learned linearly-invariant embedding and estimate a separate linear transformation instead of enforcing an identity transformation in a universal embedding | Correspondence between non-isometric FAUST point clouds · FAUST point clouds, clean and noisy | mean geodesic error | Helped |
| Use a learned linearly-invariant embedding instead of a universal embedding | Correspondence between full FAUST shapes and fragmented partial shapes · Fragmented partiality | average geodesic error | Helped |
| Use a learned linearly-invariant embedding instead of the LBO basis | Correspondence between full FAUST shapes and fragmented partial shapes · Fragmented partiality | average geodesic error | Helped |
| Add an extra linear transformation between shape embeddings rather than require corresponding points to be nearest neighbors directly (ablation) | Learned shape embedding · Non-rigid shape correspondence | correspondence accuracy | Helped |
| Use a universal embedding with identity transformation (ablation) | Correspondence between full FAUST shapes and fragmented partial shapes · Fragmented partiality | average geodesic error | Hurt |
Closest papers by meaning
- Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform (CVPR 2024 · similarity 0.88)
- DV-Matcher: Deformation-based Non-rigid Point Cloud Matching Guided by Pre-trained Visual Features (CVPR 2025 · similarity 0.88)
- Locality Preserving Refinement for Shape Matching with Functional Maps (AAAI 2024 · similarity 0.87)
- Memory-Scalable and Simplified Functional Map Learning (CVPR 2024 · similarity 0.87)
- APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction (NeurIPS 2025 · similarity 0.87)
- Denoising Functional Maps: Diffusion Models for Shape Correspondence (CVPR 2025 · similarity 0.87)
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.