DSD-MatchingNet: Deformable sparse-to-dense feature matching for learning accurate correspondences

Abstract

Background

Exploring correspondences across multiview images is the basis of various computer vision tasks. However, most existing methods have limited accuracy under challenging conditions.

Method

To learn more robust and accurate correspondences, we propose DSD-MatchingNet for local feature matching in this study. First, we develop a deformable feature extraction module to obtain multilevel feature maps, which harvest contextual information from dynamic receptive fields. The dynamic receptive fields provided by the deformable convolution network ensure that our method obtains dense and robust correspondence. Second, we utilize sparse-to-dense matching with symmetry of correspondence to implement accurate pixel-level matching, which enables our method to produce more accurate correspondences.

Result

Experiments show that our proposed DSD-MatchingNet achieves a better performance on the image matching benchmark, as well as on the visual localization benchmark. Specifically, our method achieved 91.3% mean matching accuracy on the HPatches dataset and 99.3% visual localization recalls on the Aachen Day-Night dataset.