Research map / 3D vision / Human pose estimation
Affine Correspondences between Multi-Camera Systems for 6DOF Relative Pose Estimation
Banglei Guan, Ji Zhao
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 extra affine-transformation equations E2 to the inter-camera 6DOF solver (ablation) | 2AC-inter · 6DOF solver structure | number of solutions: 56 -> 48 | Improved |
| add E2 to the intra-camera 6DOF solver (ablation) | 2AC-intra · 6DOF solver structure | solution set: 1-dim -> 48 | Improved |
| add E2 to the inter-camera solver (2AC-inter-48 vs 2AC-inter-56) (ablation) | 2AC-inter · Noise-free numerical stability | numerical stability | Hurt |
| add E2 to the inter-camera solver (ablation) | 2AC-inter · Solver runtime | runtime (us): 1084.8 -> 842.3 | Improved |
| add E2 to the 5DOF inter-camera solver (ablation) | 2AC-ka-inter · 5DOF solver structure | number of solutions: 42 -> 36 | Improved |
| add E2 to the 5DOF intra-camera solver (ablation) | 2AC-ka-intra · 5DOF solver structure | number of solutions: 44 -> 36 | Improved |
| add E2 to the 5DOF solvers (ablation) | 2AC-ka · 5DOF numerical stability | numerical stability | Hurt |
| use ACs (2 per sample) instead of PCs (6 or more) in the multi-camera solver | 2AC method · Runtime vs 6PC-Stewenius | runtime (us): 3275.4 -> 842.3 | Improved |
| use two ACs instead of 17, 8 or 6 PCs per RANSAC sample | RANSAC · outlier ratio 50%, 99.9% success | RANSAC iterations: 905410, 1765, 439 -> 25 | Improved |
| replace image point pairs of ACs with hallucinated PCs converted from ACs for PC-based solvers (ablation) | PC-based solvers · Synthetic data, random motion | rotation and translation error | Hurt |
| use larger support region (side length 40 vs 30 pixels) for AC generation (ablation) | AC-based solvers · Synthetic data | pose error | Improved |
| use inter-camera ACs instead of intra-camera ACs (ablation) | 2AC method · Synthetic data | translation scale recovery | Improved |
Closest papers by meaning
- Affine Correspondences Between Multi-Camera Systems for Relative Pose Estimation (TPAMI 2025 · similarity 0.99)
- From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation (CVPR 2024 · similarity 0.90)
- FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation (CVPR 2024 · similarity 0.90)
- Practical Solutions to the Relative Pose of Three Calibrated Cameras (CVPR 2025 · similarity 0.89)
- Relative Pose Estimation through Affine Corrections of Monocular Depth Priors (CVPR 2025 · similarity 0.88)
- Learning Affine Correspondences by Integrating Geometric Constraints (CVPR 2025 · similarity 0.86)
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.
