RANet: A relation-aware network for two-view correspondence learning

Finding true correspondences from a set of putative correspondences is a basic task in computer vision. Recent advances have demonstrated that Multi Layer Perceptrons (MLPs) can handle the unordered correspondence learning problem by training a deep classifier. However, MLPs ignore the relationship between correspondences, such as geometric information, spatial information and inlier distribution information, which will lead to difficulties in modeling complex global context. To solve this issue, we propose a Relation-Aware Network (RANet), by capturing rich global information from channel and spatial dimensions, to establish reliable correspondences for feature matching. Specifically, we firstly present a Global Context Attention block by a two-branch attention structure to cooperate with MLPs for contextual information extraction. Then, we design a Relation-Aware Filter block by further exploring the channel and spatial relationship information with different connection manners. Finally, we combine two blocks to obtain an enhanced basic block with strong feature representation capacity due to the acquisition of global contextual information. Our experiments have been conducted over both indoor and outdoor datasets on the tasks of outlier removal and camera pose estimation, which demonstrate the superiority of our network that achieves the best performance compared with the state-of-the-art approaches.