Research map / Point clouds / Registration and matching
Topology-Aware Non-Rigid Point Cloud Registration
Konstantinos Zampogiannis, Cornelia M. Fermuller, Yiannis Aloimonos
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 topology-aware backward-warp blending (ablation) | F-Warp · MPI Sintel, overall | frame-wise mean EPE: 1.379 -> 1.336 | Improved |
| add topology-aware backward-warp blending (ablation) | F-Warp · MPI Sintel, overall | frame-wise median EPE: 0.488 -> 0.487 | Improved |
| add topology-aware backward-warp blending (ablation) | F-Warp · MPI Sintel, overall | frame-wise mean AE: 7.213 -> 7.136 | Improved |
| add topology-aware backward-warp blending (ablation) | F-Warp · Dynamic topology dataset, overall | registration error (mm): 2.167 -> 1.503 | Improved |
| add topology-aware backward-warp blending (ablation) | F-Warp · Dynamic topology dataset, bot_drawer | registration error (mm): 2.380 -> 1.222 | Improved |
| add topology-aware backward-warp blending (ablation) | F-Warp · Dynamic topology dataset, drum | registration error (mm): 1.608 -> 1.207 | Improved |
| add topology-aware backward-warp blending (ablation) | F-Warp · Dynamic topology dataset, separate | registration error (mm): 2.418 -> 1.985 | Improved |
| add topology-aware backward-warp blending (ablation) | F-Warp · MPI Sintel, ambush_6 mean EPE | frame-wise mean EPE: 7.535 -> 8.028 | Hurt |
| add topology-aware backward-warp blending (ablation) | F-Warp · MPI Sintel, ambush_5 mean EPE | frame-wise mean EPE: 7.017 -> 6.411 | Improved |
Closest papers by meaning
- Topology-aware Feature Propagation for Unsupervised Non-rigid Point Cloud Correspondence (CVPR 2026 · similarity 0.89)
- Deep Graph-Based Spatial Consistency for Robust Non-Rigid Point Cloud Registration (CVPR 2023 · similarity 0.89)
- Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy (ICLR 2025 · similarity 0.88)
- HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions (AAAI 2025 · similarity 0.86)
- SPU-PMD: Self-Supervised Point Cloud Upsampling via Progressive Mesh Deformation (CVPR 2024 · similarity 0.86)
- Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation (ICML 2025 · 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.
