Learning Two-View Correspondences and Geometry Using Order-Aware Network

TL;DR

This paper introduces an Order-Aware Network that improves two-view correspondence and geometry estimation by hierarchically capturing local and global spatial context, leading to significant accuracy improvements.

Contribution

The paper presents a novel hierarchical network with three operations for inlier correspondence probability and pose regression, including a permutation-invariant clustering method.

Findings

Significant accuracy improvements over state-of-the-art methods.

Effective clustering of correspondences invariant to input permutations.

Robust estimation of two-view geometry in diverse datasets.

Abstract

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.