Research map / Architectures and efficiency / CNN design
Learning shape correspondence with anisotropic convolutional neural networks
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 anisotropic heat-kernel patches with oriented local context | ACNN · FAUST | Princeton protocol correspondence accuracy | Helped |
| Use ACNN instead of competing correspondence methods | Shape correspondence · SHREC'16 Partial (cuts) | symmetric Princeton protocol correspondence accuracy | Helped |
| Use ACNN instead of competing correspondence methods | Shape correspondence · SHREC'16 Partial (holes) | symmetric Princeton protocol correspondence accuracy | Helped |
| Add batch normalization (ablation) | FAUST ACNN · FAUST | raw soft-correspondence performance | No clear effect |
| Add dropout regularization with π_drop = 0.5 (ablation) | Partial-correspondence ACNN · SHREC'16 Partial | overfitting | Helped |
Closest papers by meaning
- Shape correspondence using anisotropic Chebyshev spectral CNNs (CVPR 2020 · similarity 0.89)
- NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go (CVPR 2021 · similarity 0.87)
- Unsupervised Learning of Dense Shape Correspondence (CVPR 2019 · similarity 0.87)
- NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matching (NeurIPS 2022 · similarity 0.87)
- Universal Correspondence Network (NeurIPS 2016 · similarity 0.87)
- 4Deform: Neural Surface Deformation for Robust Shape Interpolation (CVPR 2025 · 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.