Research map / Learning theory and algorithms / Combinatorial and search optimization
Optimal Relative Pose With Unknown Correspondences
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 |
|---|---|---|---|
| Allow multiple sufficiently good candidate matches instead of requiring unambiguous symmetric matches | Proposed relative-pose method · KITTI 0005 | rotation error (degrees): 5.31 -> 2.87 | Helped |
| Allow multiple sufficiently good candidate matches instead of requiring unambiguous symmetric matches | Proposed relative-pose method · KITTI 0005 | translation error (degrees): 13.81 -> 9.99 | Helped |
| Allow multiple sufficiently good candidate matches instead of requiring unambiguous symmetric matches | Proposed relative-pose method · KITTI 0001, 0015, and 0048 | rotation error (degrees): 1.97 -> 1.20; 1.71 -> 0.97; 0.62 -> 0.61 | Mixed |
| Allow multiple sufficiently good candidate matches instead of requiring unambiguous symmetric matches | Proposed relative-pose method · KITTI 0001, 0015, and 0048 | translation error (degrees): 7.79 -> 4.77; 9.99 -> 5.87; 2.17 -> 2.13 | Mixed |
| Include more candidate matches rather than restricting to fewer matches | Proposed translation-estimation method · 136 image pairs, varying candidate-match count | average inliers: 143 -> 724 | Helped |
| Use geometric optimization with the 10000 best candidate matches rather than Lowe's restrictive criterion | Relative-pose estimation on a repeated-window image pair · Repeated-window image pair | inlier count: 27 -> 171 | Helped |
Closest papers by meaning
- From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation (CVPR 2024 · similarity 0.91)
- Practical Solutions to the Relative Pose of Three Calibrated Cameras (CVPR 2025 · similarity 0.87)
- Structure-Aware Correspondence Learning for Relative Pose Estimation (CVPR 2025 · similarity 0.86)
- Learning Affine Correspondences by Integrating Geometric Constraints (CVPR 2025 · similarity 0.85)
- Relative Pose Estimation through Affine Corrections of Monocular Depth Priors (CVPR 2025 · similarity 0.85)
- Efficient Solution of Point-Line Absolute Pose (CVPR 2024 · 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.