Research map / Learning theory and algorithms / Combinatorial and search optimization
Deterministic Approximate Methods for Maximum Consensus Robust Fitting
Huu Le, Tat-Jun Chin, Anders P. Eriksson, Thanh-Toan Do, David Suter
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 |
|---|---|---|---|
| refine RANSAC solution with EP (non-smooth penalty Frank-Wolfe) | RANSAC · Fundamental matrix, House | consensus size: 240 -> 275 | Improved |
| refine RANSAC solution with EP | RANSAC · Homography geometric, University Library | consensus size: 136 -> 210 | Improved |
| refine RANSAC solution with EP | RANSAC · Affinity, Building 170 | consensus size: 315 -> 538 | Improved |
| refine RANSAC solution with EP instead of LO-RANSAC | LO-RANSAC · Triangulation, 11595 points | total inliers: 94387 -> 99232 | Improved |
| refine RANSAC solution with ADMM-based AM instead of EP | EP-RS · Triangulation, 11595 points | time (minutes): 49.52 -> 86.14 | Hurt |
| use ADMM (AM) instead of EP | EP-RS · Fundamental matrix, Corridor | consensus size: 375 -> 388 | No clear effect |
| initialize EP with least squares instead of RANSAC | EP · Fundamental matrix, Corridor | consensus size: 375 -> 390 | Improved |
| refine with EP-l-inf initialized from l-inf outlier removal | l-inf outlier removal · Triangulation, 11595 points | total inliers: 43869 -> 59996 | Improved |
| refine RANSAC solution with EP | RANSAC · Triangulation, 11595 points | time (minutes): 12.10 -> 49.52 | Hurt |
| add EP refinement to RANSAC | RANSAC · Linear regression, synthetic, unbalanced | consensus size | Improved |
Closest papers by meaning
- An Exact Penalty Method for Locally Convergent Maximum Consensus (CVPR 2017 · similarity 0.93)
- Robust fitting in computer vision: easy or hard? (ECCV 2018 · similarity 0.93)
- Deterministic Consensus Maximization with Biconvex Programming (ECCV 2018 · similarity 0.93)
- Efficient Globally Optimal Consensus Maximisation with Tree Search (TPAMI 2016 · similarity 0.91)
- Consensus Maximization With Linear Matrix Inequality Constraints (CVPR 2017 · similarity 0.91)
- Consensus Maximisation Using Influences of Monotone Boolean Functions (CVPR 2021 · similarity 0.90)
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.
