Research map / 3D vision / Depth and stereo
What Correspondences Reveal About Unknown Camera and Motion Models?
Thomas Probst, Ajad Chhatkuli, Danda Pani Paudel, Luc Van Gool
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 sparse-basis polynomial fitting for unknown two-view models instead of RANSAC | Synthetic correspondences across camera and motion types · Synthetic data | model fitting accuracy | Improved |
| Use sparse-basis polynomial fitting for unknown two-view models instead of RANSAC | Synthetic correspondences across camera and motion types · Synthetic data | inlier-outlier classification | Improved |
| Use sparse-basis fitting with an unknown model instead of RANSAC with the ground-truth model | Synthetic correspondences across camera and motion types · Synthetic data | inlier-outlier classification | No clear effect |
| Search for sparse polynomial bases to choose the two-view relationship | Short-baseline camera motion estimation · Oxford Robot Car | relative camera pose estimation | Improved |
| Search for sparse polynomial bases to choose the two-view relationship | Short-baseline camera motion estimation · TUM RGBD | motion estimation | Improved |
| Use sparse-basis instead of RANSAC | Short-baseline camera motion estimation · TUM RGBD | motion estimation | Improved |
| Fit the correct two-view relationship rather than a weaker Fundamental-matrix constraint | Correspondences related by a homography · Synthetic data | outlier detection | Improved |
| Use sparse-basis to estimate the two-view relationship | SIFT correspondences in identical images at different resolutions · Real image matching | inlier detection | Improved |
Closest papers by meaning
- Automatic Camera Calibration Using Multiple Sets of Pairwise Correspondences (TPAMI 2017 · similarity 0.88)
- AnyMap: Learning a General Camera Model for Structure-from-Motion with Unknown Distortion in Dynamic Scenes (CVPR 2025 · similarity 0.85)
- From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation (CVPR 2024 · similarity 0.84)
- Structure-Aware Correspondence Learning for Relative Pose Estimation (CVPR 2025 · similarity 0.84)
- VGGSfM: Visual Geometry Grounded Deep Structure From Motion (CVPR 2024 · similarity 0.84)
- Unifying Correspondence Pose and NeRF for Generalized Pose-Free Novel View Synthesis (CVPR 2024 · 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.
