Research map / Point clouds / Registration and matching
Efficient Global Point Cloud Alignment Using Bayesian Nonparametric Mixtures
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the proposed 4D tetrahedral rotation tessellation instead of axis-angle tessellation (ablation) | Branch and bound rotation search · Stanford Bunny | computation time per iteration: by an order of magnitude | Helped |
| Add surface-normal-based rotational alignment | Global point cloud alignment · Happy Buddha | alignment success | Helped |
| Add Manhattan World symmetry search over 24 rotations (ablation) | BB with scale search · Apartment Dataset | registration accuracy | Helped |
| Add Manhattan World symmetry search over 24 rotations (ablation) | BB with scale search · Apartment Dataset | speedup over GOGMA: 3x | Helped |
| Ignore Manhattan World symmetry (ablation) | BB rotational alignment · Apartment Dataset | mean registration error | Hurt |
| Use point-based or GMM-based rotational alignment instead of surface normals (ablation) | Global alignment on scans with anisotropic normal distributions · Happy Buddha | alignment success | Hurt |
| Add local ICP refinement after BB (ablation) | BB alignment · Stanford Bunny partial scans | alignment quality | Helped |
Closest papers by meaning
- Consistent Normal Orientation for 3D Point Clouds via Least Squares on Delaunay Graph (CVPR 2025 · similarity 0.87)
- Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy (ICLR 2025 · similarity 0.86)
- Rectified Point Flow: Generic Point Cloud Pose Estimation (NeurIPS 2025 · similarity 0.86)
- Multiway Point Cloud Mosaicking with Diffusion and Global Optimization (CVPR 2024 · similarity 0.86)
- PointMC: Multi-instance Point Cloud Registration based on Maximal Cliques (ICML 2024 · similarity 0.86)
- DV-Matcher: Deformation-based Non-rigid Point Cloud Matching Guided by Pre-trained Visual Features (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.