Research map / Point clouds / Registration and matching
Shape Registration in the Time of Transformers
Giovanni Trappolini, Luca Cosmo, Luca Moschella, Riccardo Marin, Simone Melzi, Emanuele Rodolà
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 |
|---|---|---|---|
| apply latent-space refinement at test time | Our · FAUST | average geodesic error: 0.0513 -> 0.0369 | Improved |
| apply latent-space refinement at test time | Our · FAUST(1k) | average geodesic error: 0.0419 -> 0.0263 | Improved |
| apply latent-space refinement at test time | Our · SHREC19 | average geodesic error: 0.0802 -> 0.0615 | Improved |
| apply latent-space refinement at test time | Our · FAUST(1k-outliers) | average geodesic error: 0.1657 -> 0.1479 | Improved |
| use 8 rather than 32 latent vectors (ablation) | Our · SURREAL and FAUST | relative average matching error: SURREAL: 1.00 -> 0.93; FAUST: 1.00 -> 1.24 | Mixed |
| use 2 rather than 32 latent vectors (ablation) | Our · SURREAL and FAUST | relative average matching error: SURREAL: 1.00 -> 0.91; FAUST: 1.00 -> 1.29 | Mixed |
| use 4 rather than 8 encoder-decoder layers (ablation) | Our · SURREAL and FAUST | relative average matching error: SURREAL: 1.00 -> 1.04; FAUST: 1.00 -> 1.45 | Mixed |
| use 12 rather than 8 encoder-decoder layers (ablation) | Our · SURREAL and FAUST | relative average matching error: SURREAL: 1.00 -> 0.93; FAUST: 1.00 -> 1.22 | Mixed |
| use 32 rather than 64 latent dimensions (ablation) | Our · SURREAL and FAUST | relative average matching error: SURREAL: 1.00 -> 1.36; FAUST: 1.00 -> 0.82 | Mixed |
| use 128 rather than 64 latent dimensions (ablation) | Our · SURREAL and FAUST | relative average matching error: SURREAL: 1.00 -> 1.45; FAUST: 1.00 -> 0.94 | Mixed |
| replace classic point attention with density-aware surface attention | Our transformer registration model · FAUST | matching error | Improved |
| train on only a sparse fraction of ground-truth correspondences | Our · registration training | matching quality: 10\sim20\% | No clear effect |
Closest papers by meaning
- RGGT: A Generative-Prior-Guided Transformer for Unified Rigid and Non-Rigid Point Cloud Registration (ICML 2026 · similarity 0.90)
- Geometric Transformer for Fast and Robust Point Cloud Registration (CVPR 2022 · similarity 0.89)
- GeoTransformer: Fast and Robust Point Cloud Registration With Geometric Transformer (TPAMI 2023 · similarity 0.89)
- Unsupervised Template-assisted Point Cloud Shape Correspondence Network (CVPR 2024 · similarity 0.86)
- DiffCorr: Conditional Diffusion Model with Reliable Pseudo-Label Guidance for Unsupervised Point Cloud Shape Correspondence (AAAI 2025 · similarity 0.86)
- Dynamic Cues-Assisted Transformer for Robust Point Cloud Registration (CVPR 2024 · similarity 0.86)
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.
