Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence
This work addresses robust geometric matching for computer vision applications, representing an incremental improvement with novel method elements.
The authors tackled the problem of establishing reliable visual correspondences under large image variations by introducing Convolutional Hough Matching (CHM), which distributes similarities over a geometric transformation space and learns non-rigid matching with interpretable parameters, achieving state-of-the-art results on semantic visual correspondence benchmarks.
Despite advances in feature representation, leveraging geometric relations is crucial for establishing reliable visual correspondences under large variations of images. In this work we introduce a Hough transform perspective on convolutional matching and propose an effective geometric matching algorithm, dubbed Convolutional Hough Matching (CHM). The method distributes similarities of candidate matches over a geometric transformation space and evaluates them in a convolutional manner. We cast it into a trainable neural layer with a semi-isotropic high-dimensional kernel, which learns non-rigid matching with a small number of interpretable parameters. To further improve the efficiency of high-dimensional voting, we also propose to use an efficient kernel decomposition with center-pivot neighbors, which significantly sparsifies the proposed semi-isotropic kernels without performance degradation. To validate the proposed techniques, we develop the neural network with CHM layers that perform convolutional matching in the space of translation and scaling. Our method sets a new state of the art on standard benchmarks for semantic visual correspondence, proving its strong robustness to challenging intra-class variations.