Research map / Learning theory and algorithms / Combinatorial and search optimization
GOGMA: Globally-Optimal Gaussian Mixture Alignment
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 |
|---|---|---|---|
| Refine GOGMA output with local GMA using about 1000 components (ablation) | GOGMA · stairs | fine inlier rate (%): 80.0 -> 99.7 | Helped |
| Refine GOGMA output with local GMA using about 1000 components (ablation) | GOGMA · wood-summer | fine inlier rate (%): 16.7 -> 99.9 | Helped |
| Use SVGM rather than KDE for the GMM representation (ablation) | GOGMA · dragon fully-overlapping registration | mean translation error (m): 0.14/0.21 -> 0.004/0.008 | Helped |
| Use SVGM rather than EM for the GMM representation (ablation) | GOGMA · dragon fully-overlapping registration | mean runtime (s): 4960/4965 -> 34/50 | Helped |
| Use SVGM rather than KDE for the GMM representation (ablation) | GOGMA · dragon fully-overlapping registration | mean runtime (s): 15/15 -> 34/50 | Hurt |
| Use local ICP or CPD instead of globally optimal GOGMA | 3D point-set registration · stairs and wood-summer | coarse registration inlier rate (%): GOGMA 100; ICP 15.5 and 11.3; CPD 38.8 and 39.5 | Hurt |
Closest papers by meaning
- Cross-Instance Gaussian Splatting Registration via Geometry-Aware Feature-Guided Alignment (CVPR 2026 · similarity 0.87)
- The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation (CVPR 2019 · similarity 0.86)
- Efficient Global Point Cloud Alignment Using Bayesian Nonparametric Mixtures (CVPR 2017 · similarity 0.86)
- GRICP: Granular-Ball Iterative Closest Point with Multikernel Correntropy for Point Cloud Fine Registration (AAAI 2025 · similarity 0.85)
- Scalable 3D Registration via Truncated Entry-wise Absolute Residuals (CVPR 2024 · similarity 0.83)
- Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis (CVPR 2024 · similarity 0.82)
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.