Research map / 3D vision / Face and shape
Region-Based Correspondence Between 3D Shapes via Spatially Smooth Biclustering
Matteo Denitto, Simone Melzi, Manuele Bicego, Umberto Castellani, Alessandro Farinelli, Mario A. T. Figueiredo, Yanir Kleiman, Maks Ovsjanikov
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 |
|---|---|---|---|
| add geodesic spatial smoothness prior (ablation) | S4B biclustering · FAUST global | mean labelling accuracy: 31.8 -> 94.8 | Improved |
| add geodesic spatial smoothness prior (ablation) | S4B biclustering · FAUST global | median labelling accuracy: 31.26 -> 95.52 | Improved |
| add geodesic spatial smoothness prior (ablation) | S4B biclustering · FAUST scenario 1 | mean labelling accuracy: 29.91 -> 97.36 | Improved |
| add geodesic spatial smoothness prior (ablation) | S4B biclustering · FAUST scenario 3 | mean labelling accuracy: 32.32 -> 94.25 | Improved |
| use S4B instead of SRC for region correspondence | region-based correspondence · FAUST global | mean labelling accuracy: 86.58 -> 94.8 | Improved |
| use S4B instead of SRC for region correspondence | region-based correspondence · FAUST scenario 2 | mean labelling accuracy: 85.34 -> 95.73 | Improved |
| use S4B instead of BIM with Voronoi segmentation | region-based correspondence · FAUST global | mean labelling accuracy: 93.26 -> 94.8 | Improved |
| use S4B instead of BIM with Voronoi segmentation | region-based correspondence · FAUST scenario 1 | median labelling accuracy: 96.76 -> 97.98 | Improved |
| start BIM from S4B labels instead of Voronoi cells | BIM · FAUST global | mean labelling accuracy: 93.26 -> 93.36 | No clear effect |
| start BIM from S4B labels instead of Voronoi cells | BIM · FAUST scenario 2 | mean labelling accuracy: 95.35 -> 94.21 | Hurt |
| add S4B region indicators to functional maps | functional maps point-wise map estimation · FAUST | correct matches vs localization error | Improved |
| add SRC region indicators to functional maps (versus S4B regions) | functional maps point-wise map estimation · FAUST | correct matches vs localization error | Mixed |
Closest papers by meaning
- Partial-to-Partial Shape Matching with Geometric Consistency (CVPR 2024 · similarity 0.87)
- Multi-Shape Matching with Cycle Consistency Basis via Functional Maps (AAAI 2025 · similarity 0.86)
- EchoMatch: Partial-to-Partial Shape Matching via Correspondence Reflection (CVPR 2025 · similarity 0.86)
- Higher-Order Ratio Cycles for Fast and Globally Optimal Shape Matching (CVPR 2025 · similarity 0.86)
- SegMASt3R: Geometry Grounded Segment Matching (NeurIPS 2025 · similarity 0.86)
- Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondence (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.
