Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence

by   Juhong Min, et al.

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.


page 1

page 7

page 8

page 10

page 11

page 12


Convolutional Hough Matching Networks

Despite advances in feature representation, leveraging geometric relatio...

Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence

Existing pipelines of semantic correspondence commonly include extractin...

Learning to Compose Hypercolumns for Visual Correspondence

Feature representation plays a crucial role in visual correspondence, an...

Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features

Establishing visual correspondences under large intra-class variations r...

Attentive Semantic Alignment with Offset-Aware Correlation Kernels

Semantic correspondence is the problem of establishing correspondences a...

Correspondence Networks with Adaptive Neighbourhood Consensus

In this paper, we tackle the task of establishing dense visual correspon...

Universal Correspondence Network

We present a deep learning framework for accurate visual correspondences...

Code Repositories


Official PyTorch Implementation of Convolutional Hough Matching Networks, CVPR 2021 (oral)

view repo

Please sign up or login with your details

Forgot password? Click here to reset