Graph-Cut RANSAC

作者：Dániel Baráth, Jiřı́ Matas · 年份：2018 · DOI：10.1109/cvpr.2018.00704 · 被引用次数：359 · 研究领域：Advanced Image and Video Retrieval Techniques、Robotics and Sensor-Based Localization、Advanced Neural Network Applications

A novel method for robust estimation, called Graph-Cut RANSAC1, 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).