Research map / Label-efficient and robust learning / Self-supervised and contrastive
Cyclic Functional Mapping: Self-supervised Correspondence between Non-isometric Deformable Shapes
Dvir Ginzburg, Dan Raviv
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 cyclic self-supervised mapping instead of Litany et al. | deep functional maps · FAUST scans, inter-subject | average geodesic error: 4.826 -> 4.068 | Improved |
| use cyclic self-supervised mapping instead of Litany et al. | deep functional maps · FAUST scans, intra-subject | average geodesic error: 2.436 -> 2.12 | Improved |
| use cyclic mapping instead of Litany et al. | deep functional maps · FAUST synthetic, inter-subject | average geodesic error: 2.452 -> 2.327 | Improved |
| use cyclic mapping instead of Litany et al. | deep functional maps · FAUST synthetic, intra-subject | average geodesic error: 2.125 -> 2.112 | No clear effect |
| use cyclic mapping instead of Halimi et al. isometric unsupervised loss | deep functional maps · FAUST synthetic, inter-subject | average geodesic error: 3.632 -> 2.327 | Improved |
| use cyclic mapping instead of Halimi et al. isometric unsupervised loss | deep functional maps · FAUST scans, inter-subject | average geodesic error: 4.883 -> 4.068 | Improved |
| self-supervised cyclic mapping versus supervised Groueix et al. | deep functional maps · FAUST scans, intra-subject | average geodesic error: 2.789 -> 2.12 | Improved |
| self-supervised cyclic mapping versus supervised Li et al. | deep functional maps · FAUST scans, inter-subject | average geodesic error: 4.079 -> 4.068 | No clear effect |
Closest papers by meaning
- Deep Functional Maps: Structured Prediction for Dense Shape Correspondence (ICCV 2017 · similarity 0.91)
- Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence (CVPR 2020 · similarity 0.89)
- Spatially and Spectrally Consistent Deep Functional Maps (ICCV 2023 · similarity 0.89)
- Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching (CVPR 2024 · similarity 0.89)
- Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform (CVPR 2024 · similarity 0.88)
- Memory-Scalable and Simplified Functional Map Learning (CVPR 2024 · similarity 0.88)
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.
