Research map / Point clouds / Registration and matching
Minimal Solvers for Mini-Loop Closures in 3D Multi-Scan Alignment
Pedro Miraldo, Surojit Saha, Srikumar Ramalingam
Check 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 |
|---|---|---|---|
| Replace pairwise registration with joint 3-cycle registration | 3D scan alignment · TUM 5-scan sequences | rotation error (degrees): 0.90 -> 0.80 | Improved |
| Replace pairwise registration with joint 3-cycle registration | 3D scan alignment · TUM 5-scan sequences | translation error (centimeters): 2.53 -> 2.44 | Improved |
| Replace pairwise registration with a 4-cycle followed by pairwise registration | 3D scan alignment · TUM 5-scan sequences | rotation error (degrees): 0.90 -> 0.80 | Improved |
| Replace pairwise registration with a 4-cycle followed by pairwise registration | 3D scan alignment · TUM 5-scan sequences | translation error (centimeters): 2.53 -> 2.47 | Improved |
| Replace pairwise registration with joint 5-cycle registration | 3D scan alignment · TUM 5-scan sequences | rotation error (degrees): 0.90 -> 0.77 | Improved |
| Replace pairwise registration with joint 5-cycle registration | 3D scan alignment · TUM 5-scan sequences | translation error (centimeters): 2.53 -> 2.60 | Hurt |
| Use longer mini-cycles rather than pairwise registration | 3D scan alignment solver · Synthetic 3D scan alignment | computation time (ms): 0.0392 -> 0.1192; 0.0392 -> 3.3422; 0.0392 -> 24.954 | Hurt |
| Use mini-cycle solvers instead of pairwise methods | 3D scan alignment · Synthetic data with Gaussian noise | rotation and translation error | Improved |
| Use 5-cycle registration rather than the other tested methods | 3D scan alignment · Synthetic data with Gaussian noise | inlier percentage | Hurt |
| Use n-cycle methods rather than pairwise registration | 3D scan alignment · TUM 5-scan sequences | rotation and translation error | Mixed |
Closest papers by meaning
- Minimal Solvers for 3D Scan Alignment With Pairs of Intersecting Lines (CVPR 2020 · similarity 0.90)
- SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration (TPAMI 2025 · similarity 0.86)
- Fast Rotation Search with Stereographic Projections for 3D Registration (TPAMI 2016 · similarity 0.85)
- Deterministic Point Cloud Registration via Novel Transformation Decomposition (CVPR 2022 · similarity 0.85)
- Scalable 3D Registration via Truncated Entry-wise Absolute Residuals (CVPR 2024 · similarity 0.85)
- Practical Solutions to the Relative Pose of Three Calibrated Cameras (CVPR 2025 · similarity 0.84)
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.
