Research map / 3D vision / Human pose estimation
On the Instability of Relative Pose Estimation and RANSAC's Role
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 |
|---|---|---|---|
| Use distance from the seventh correspondence to the 6.5-point curve as a stability indicator | Uncalibrated 7-point relative pose estimation · Synthetic uncalibrated 7-point problems | distance to 6.5-point curve (pixels): 2.35 (unstable) vs 22.12 (stable) | Mixed |
| Use distance from the fifth correspondence to the 4.5-point curve as a stability indicator | Calibrated 5-point relative pose estimation · Synthetic calibrated 5-point problems | distance to 4.5-point curve (pixels): 14.95 (unstable) vs 0.32 (stable) | Mixed |
| Select hypotheses using RANSAC consensus, which also favors well-conditioned image data | 5-point and 7-point relative pose estimation · All-inlier relative pose estimation | stability of pose estimate | Helped |
| Use minimal image data close to the degenerate X.5-point curve | 5-point and 7-point relative pose estimation · Synthetic and real-world image data | stability of pose estimate | Hurt |
Closest papers by meaning
- Minimal Solutions for Relative Pose With a Single Affine Correspondence (CVPR 2020 · similarity 0.89)
- CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus (CVPR 2020 · similarity 0.88)
- PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus (AAAI 2024 · similarity 0.87)
- From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation (CVPR 2024 · similarity 0.86)
- Noisy One-point Homographies are Surprisingly Good (CVPR 2024 · similarity 0.86)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 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.