Research map / Point clouds / Registration and matching
Deterministic Point Cloud Registration via Novel Transformation Decomposition
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 |
|---|---|---|---|
| Decompose the 6-DOF transform into sequential (2+1)-DOF and (1+2)-DOF searches using branch and bound | Point cloud registration · 3DMatch | SR (%): 91.68 -> 92.98 | Helped |
| Use TR-DE rather than PointDSC | Point cloud registration · 3DMatch | Time (s): 0.02 -> 0.16 | Hurt |
| Use TR-DE rather than PointDSC | Point cloud registration · 3DLoMatch with FCGF descriptors | SR (%) | Mixed |
| Use TR-DE rather than PointDSC | Point cloud registration · 3DLoMatch with Predator descriptors | SR (%) | Helped |
| Use TR-DE rather than RANSAC-10k | Point cloud registration · KITTI with FCGF descriptors | SR (%): 98.02 -> 98.2 | Helped |
| Use TR-DE rather than PointDSC | Point cloud registration · KITTI with FCGF descriptors | RE (°): 0.33 -> 0.38 | Hurt |
| Use TR-DE rather than PointDSC | Point cloud registration · KITTI with FCGF descriptors | TE (cm): 20.99 -> 18 | Helped |
| Replace pairwise registration with TR-DE | Multi-way registration pipeline · Augmented ICL-NUIM, AVG | ATE (cm): 17.61 -> 14.2 | Helped |
| Use the proposed (2+1)/(1+2)-DOF decomposition and nested branch-and-bound search | Deterministic point cloud registration · Synthetic dataset, correspondence count increased from 2000 to 4000 | Time (s) | Helped |
Closest papers by meaning
- A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization (NeurIPS 2024 · similarity 0.91)
- Register Anything Model for Generalizable and Robust Point Cloud Registration (NeurIPS 2026 · similarity 0.90)
- Where Precision Meets Efficiency: Transformation Diffusion Model for Point Cloud Registration (AAAI 2025 · similarity 0.88)
- Scalable 3D Registration via Truncated Entry-wise Absolute Residuals (CVPR 2024 · similarity 0.88)
- Inlier Confidence Calibration for Point Cloud Registration (CVPR 2024 · similarity 0.87)
- Consistent Normal Orientation for 3D Point Clouds via Least Squares on Delaunay Graph (CVPR 2025 · similarity 0.87)
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.