MAGSAC: Marginalizing Sample Consensus

Daniel Barath, Jiri Matas, Jana Noskova
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
A method called, σ-consensus, is proposed to eliminate the need for a user-defined inlier-outlier threshold in RANSAC. Instead of estimating the noise σ, it is marginalized over a range of noise scales. The optimized model is obtained by weighted least-squares fitting where the weights come from the marginalization over σ of the point likelihoods of being inliers. A new quality function is proposed not requiring σ and, thus, a set of inliers to determine the model quality. Also, a new
more » ... so, a new termination criterion for RANSAC is built on the proposed marginalization approach. Applying σ-consensus, MAGSAC is proposed with no need for a user-defined σ and improving the accuracy of robust estimation significantly. It is superior to the state-ofthe-art in terms of geometric accuracy on publicly available real-world datasets for epipolar geometry (F and E) and homography estimation. In addition, applying σ-consensus only once as a post-processing step to the RANSAC output always improved the model quality on a wide range of vision problems without noticeable deterioration in processing time, adding a few milliseconds. 1
doi:10.1109/cvpr.2019.01044 dblp:conf/cvpr/BarathMN19 fatcat:2qevsrm7arcdhmhhkagjx557zi