Research map / 3D vision / Depth and stereo
Homography From Two Orientation- and Scale-Covariant Features
Daniel Barath, Zuzana Kukelova
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 |
|---|---|---|---|
| use 2SIFT minimal solver (2 correspondences) instead of 4PT | GC-RANSAC homography · AdelaideRMF | GC-RANSAC iterations: 26\;082 -> 877 | Improved |
| use 2SIFT instead of 4PT | GC-RANSAC homography · AdelaideRMF | time (s): 2.989 -> 0.092 | Improved |
| use 2SIFT instead of 4PT | GC-RANSAC homography · Multi-H | time (s): 300.645 -> 57.921 | Improved |
| use 2SIFT instead of 4PT | GC-RANSAC homography · Strecha | time (s): 10.246 -> 1.435 | Improved |
| use 2SIFT instead of 4PT | GC-RANSAC homography · Strecha | mean re-projection error (px): 1.25 -> 1.42 | Hurt |
| use 2SIFT instead of 4PT | GC-RANSAC homography · Multi-H | mean re-projection error (px): 1.87 -> 1.90 | No clear effect |
| use 2SIFT instead of 4PT | GC-RANSAC homography · AdelaideRMF | mean re-projection error (px): 1.61 -> 1.57 | Improved |
| use 2SIFT instead of 3ORI | GC-RANSAC homography · Multi-H | mean re-projection error (px): 3.41 -> 1.90 | Improved |
| use 2SIFT instead of 3ORI | GC-RANSAC homography · AdelaideRMF | GC-RANSAC iterations: 9\;772 -> 877 | Improved |
| use 2SIFT instead of 4PT | RANSAC theory, outlier ratio 0.90 · RANSAC theoretical iterations | iterations: 46\;049 -> 458 | Improved |
Closest papers by meaning
- Noisy One-point Homographies are Surprisingly Good (CVPR 2024 · similarity 0.87)
- On Making SIFT Features Affine Covariant (IJCV 2023 · similarity 0.87)
- Unsupervised Global and Local Homography Estimation With Motion Basis Learning (TPAMI 2022 · similarity 0.86)
- Symmetry-Robust 3D Orientation Estimation (ICML 2025 · similarity 0.85)
- Adapting Dense Matching for Homography Estimation with Grid-based Acceleration (CVPR 2025 · similarity 0.84)
- MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography Estimation (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.
