Learning Two-View Correspondences and Geometry Using Order-Aware Network
This work addresses the challenge of robust two-view geometry estimation for computer vision applications, representing an incremental advancement with novel operations.
The paper tackles the problem of establishing correspondences between two images by proposing an Order-Aware Network that infers inlier probabilities and regresses the relative pose, achieving significant improvements in accuracy on both outdoor and indoor datasets over state-of-the-art methods.
Establishing correspondences between two images requires both local and global spatial context. Given putative correspondences of feature points in two views, in this paper, we propose Order-Aware Network, which infers the probabilities of correspondences being inliers and regresses the relative pose encoded by the essential matrix. Specifically, this proposed network is built hierarchically and comprises three novel operations. First, to capture the local context of sparse correspondences, the network clusters unordered input correspondences by learning a soft assignment matrix. These clusters are in a canonical order and invariant to input permutations. Next, the clusters are spatially correlated to form the global context of correspondences. After that, the context-encoded clusters are recovered back to the original size through a proposed upsampling operator. We intensively experiment on both outdoor and indoor datasets. The accuracy of the two-view geometry and correspondences are significantly improved over the state-of-the-arts. Code will be available at https://github.com/zjhthu/OANet.git.