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
• DOI: 10.1109/CVPR.2018.00282

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 recover the relative pose, as encoded by the essential matrix. Our architecture is based on a multi-layer perceptron operating on pixel coordinates rather than directly on the image, and is thus simple and small. We introduce a novel normalization technique, called Context Normalization, which allows us to process each data point separately while embedding global information in it, and also makes the network invariant to the order of the correspondences. Our experiments on multiple challenging datasets demonstrate that our method is able to drastically improve the state of the art with little training data.