Learning to Compare Image Patches via Convolutional Neural Networks

Abstract

We show how to learn directly from image data (i.e., without resorting to manually-designed features) a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems. To encode such a function, we opt for a CNN-based model that is trained to account for a wide variety of changes in image appearance. To that end, we explore and study multiple neural network architectures, which are specifically adapted to this task. We show that such an approach can significantly outperform the state-of-the-art (June 2015) on several problems and benchmark datasets.

Github project page (code and models)

[paper] [arxiv] [extended abstract] [supplementary material] [poster]

Reference

Learning to Compare Image Patches via Convolutional Neural Networks
Sergey Zagoruyko, Nikos Komodakis
In Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, June 2015
[bib]