Graph-Cut RANSAC
This method improves robust estimation for computer vision tasks, offering incremental gains in accuracy while maintaining speed.
The authors tackled robust estimation by introducing Graph-Cut RANSAC, which uses graph-cut in local optimization to separate inliers and outliers, resulting in higher geometric accuracy than state-of-the-art methods across problems like line fitting and essential matrix estimation, with real-time performance comparable to less accurate alternatives.
A novel method for robust estimation, called Graph-Cut RANSAC, GC-RANSAC in short, is introduced. To separate inliers and outliers, it runs the graph-cut algorithm in the local optimization (LO) step which is applied when a so-far-the-best model is found. The proposed LO step is conceptually simple, easy to implement, globally optimal and efficient. GC-RANSAC is shown experimentally, both on synthesized tests and real image pairs, to be more geometrically accurate than state-of-the-art methods on a range of problems, e.g. line fitting, homography, affine transformation, fundamental and essential matrix estimation. It runs in real-time for many problems at a speed approximately equal to that of the less accurate alternatives (in milliseconds on standard CPU).