Research map / Point clouds / Point cloud classification
Nonparametric Continuous Sensor Registration
William Clark, Maani Ghaffari, Anthony Bloch
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 CVO instead of DVO on validation fr1 sequences | CVO · TUM fr1 validation (average) | RPE translational RMSE: 0.1544 -> 0.0631 | Improved |
| use CVO instead of DVO on fr1 training sequences | CVO · TUM fr1 training (average) | RPE translational RMSE: 0.0623 -> 0.0561 | Improved |
| use CVO instead of DVO on fr1 training sequences | CVO · TUM fr1 training (average) | RPE rotational RMSE: 2.6943 vs 2.7380 | No clear effect |
| use CVO instead of DVO on structure-texture sequences | CVO · TUM structure vs texture (training average) | RPE translational RMSE: 0.1386 -> 0.0631 | Improved |
| use CVO instead of DVO on structure-texture sequences (validation) | CVO · TUM structure vs texture (validation average) | RPE rotational RMSE: 3.8797 -> 2.4640 | Improved |
| use CVO instead of DVO when both structure and texture are rich | CVO · TUM structure+texture far (training) | RPE translational RMSE: 0.0171 -> 0.0409 | Hurt |
| shrink kernel length-scale as iterations proceed | CVO · globe registration | registration accuracy: ||T.A||_F = 0.0040 | Improved |
| decrease kernel length-scale from 0.5 to 0.2 on the torus (ablation) | kernel correlation function · torus point clouds | number of local maxima: 33 local maxima at length-scale 0.2 | Hurt |
Closest papers by meaning
- Generalized-CVO: Fast and Correspondence-Free Local Point Cloud Registration with Second Order Riemannian Optimization (CVPR 2026 · similarity 0.86)
- Multiway Non-Rigid Point Cloud Registration via Learned Functional Map Synchronization (TPAMI 2022 · similarity 0.86)
- Coherent Point Drift Revisited for Non-Rigid Shape Matching and Registration (CVPR 2022 · similarity 0.85)
- Efficient and Robust Registration on the 3D Special Euclidean Group (ICCV 2019 · similarity 0.85)
- Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy (ICLR 2025 · similarity 0.85)
- Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis (CVPR 2024 · similarity 0.83)
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.
