Research map / Point clouds / Registration and matching
Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search
Yinlong Liu, Chen Wang, Zhijian Song, Manning Wang
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 local refinement (GoTS+) (ablation) | GoTS · ArmadilloStand60/30 | rotation error (deg): 0.94 -> 0.84 | Improved |
| add local refinement (GoTS+) (ablation) | GoTS · ArmadilloStand30/0 | rotation error (deg): 1.82 -> 1.70 | Improved |
| add local refinement (GoTS+) (ablation) | GoTS · bun090/000 | rotation error (deg): 3.82 -> 3.55 | Improved |
| add local refinement (GoTS+) (ablation) | GoTS · bun045/000 | rotation error (deg): 3.95 -> 3.94 | No clear effect |
| add local refinement (GoTS+) (ablation) | GoTS · Bunny with 10% outliers | inlier RMSE: 1.03E-02 -> 1.38E-15 | Improved |
| GoTS instead of Go-ICP | global registration · Bunny with 10% outliers | inlier RMSE: 8.95E-06 -> 1.03E-02 | Hurt |
| GoTS instead of Go-ICP | global registration · bunny, varying number of points | run time | Improved |
| GoTS instead of Go-ICP | global registration · bun090/000 | rotation error (deg): 90.24 -> 3.82 | Improved |
| GoTS instead of Go-ICP | global registration · bun090/000 | run time (s): 603.63 -> 56.39 | Improved |
| GoTS instead of Go-ICP | global registration · LivingRoom frames 1 and 6 | rotation error (deg): 158.3 -> 4.382 | Improved |
| GoTS instead of Glob-GM | global registration · LivingRoom frames 1 and 6 | run time (s): 633.8 -> 25.90 | Improved |
| GoTS instead of Glob-GM | global registration · Bunny with 50% outliers | inlier RMSE: 1.41E-01 -> 1.17E-02 | Improved |
Closest papers by meaning
- Fast Rotation Search with Stereographic Projections for 3D Registration (TPAMI 2016 · similarity 0.92)
- Efficient and Robust Point Cloud Registration via Heuristics-Guided Parameter Search (TPAMI 2024 · similarity 0.90)
- Deterministic Point Cloud Registration via Novel Transformation Decomposition (CVPR 2022 · similarity 0.89)
- (Just) A Spoonful of Refinements Helps the Registration Error Go Down (ICCV 2021 · similarity 0.89)
- SHReg: Strictly Rotation-Equivariant Point Cloud Registration via Spherical Harmonics (ECCV 2026 · similarity 0.88)
- A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization (NeurIPS 2024 · 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.
