Research map / 3D vision / Human pose estimation
Globally Optimal Relative Pose Estimation With Gravity Prior
Yaqing Ding, Daniel Barath, Jian Yang, Hui Kong, Zuzana Kukelova
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 |
|---|---|---|---|
| Use LIN instead of 5PC for non-minimal fitting | GC-RANSAC with 5PC minimal fitting · Malaga | rotation error (degrees): 2.72 -> 2.41 | Improved |
| Use LIN instead of 5PC for non-minimal fitting | GC-RANSAC with 5PC minimal fitting · Malaga | translation error (degrees): 4.79 -> 3.49 | Improved |
| Use LIN instead of 5PC for non-minimal fitting | GC-RANSAC with 5PC minimal fitting · KITTI | rotation error (degrees): 0.27 -> 0.05 | Improved |
| Use LIN instead of 5PC for non-minimal fitting | GC-RANSAC with 5PC minimal fitting · KITTI | translation error (degrees): 3.30 -> 1.89 | Improved |
| Use LIN instead of 5PC for non-minimal fitting | GC-RANSAC with 5PC minimal fitting · ETH3D | rotation error (degrees): 2.15 -> 0.37 | Improved |
| Use LIN instead of 5PC for non-minimal fitting | GC-RANSAC with 5PC minimal fitting · ETH3D | translation error (degrees): 36.74 -> 26.86 | Improved |
| Replace polynomial eigenvalue solving with Sturm sequences | OPT relative pose solver · relative pose estimation, synthetic data | solver time (μs): 115 -> 24 | Improved |
| Use first-order rotation approximation | relative pose solver · relative pose estimation, synthetic data | solver time (μs): 115 -> 54 | Improved |
| Combine first-order rotation approximation with Sturm sequences | relative pose solver · relative pose estimation, synthetic data | solver time (μs): 115 -> 13 | Improved |
Closest papers by meaning
- Gravity-aware partially calibrated absolute pose estimation from affine- or rotation-covariant features (ECCV 2026 · similarity 0.89)
- Homography-Based Minimal-Case Relative Pose Estimation With Known Gravity Direction (TPAMI 2020 · similarity 0.88)
- Absolute Pose from One or Two Scaled and Oriented Features (CVPR 2024 · similarity 0.86)
- From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation (CVPR 2024 · similarity 0.86)
- Practical Solutions to the Relative Pose of Three Calibrated Cameras (CVPR 2025 · similarity 0.85)
- Relative Pose Estimation through Affine Corrections of Monocular Depth Priors (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.
