Convolutional Hough Matching Networks
This work addresses the challenge of robust visual matching for computer vision applications, particularly under intra-class variations, representing an incremental improvement with a novel method for a known bottleneck.
The authors tackled the problem of establishing reliable visual correspondences under large image variations by introducing Convolutional Hough Matching (CHM), a geometric matching algorithm that distributes similarities over a transformation space and learns non-rigid matching with interpretable parameters, achieving new state-of-the-art results on standard benchmarks for semantic visual correspondence.
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 evaluate 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 validate the effect, 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.