Learning to Find Good Correspondences

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 2666 - 2674
• Main Authors: Yi, Kwang Moo, Trulls, Eduard, Ono, Yuki, Lepetit, Vincent, Salzmann, Mathieu, Fua, Pascal
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Cameras; Feature extraction; Geometry; Pipelines; Sparse matrices; Three-dimensional displays; Training

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outliers, while simultaneously using them to recov...