Learning to Find Good Correspondences
This work addresses the challenge of robust correspondence estimation in computer vision, which is crucial for applications like 3D reconstruction and robotics, representing a significant advance over existing methods.
The paper tackles the problem of identifying reliable correspondences for wide-baseline stereo by developing a deep learning architecture that labels matches as inliers or outliers and recovers the relative pose, achieving a drastic improvement in state-of-the-art performance with minimal training data.
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 imbuing it with global information, 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.