Estimating a depth map from multiple views of a scene is a fundamental task in computer vision. As soon as more than two viewpoints are available, one faces the very basic question how to measure similarity across >2 image patches. Surprisingly, no direct solution exists, instead it is common to fall back to more or less robust averaging of two-view similarities. Encouraged by the success of machine learning, and in particular convolutional neural networks, we propose to learn a matching function which directly maps multiple image patches to a scalar similarity score. Experiments on several multi-view datasets demonstrate that this approach has advantages over methods based on pairwise patch similarity.
@article{arxiv.1703.08836,
title = {Learned Multi-Patch Similarity},
author = {Wilfried Hartmann and Silvano Galliani and Michal Havlena and Luc Van Gool and Konrad Schindler},
journal= {arXiv preprint arXiv:1703.08836},
year = {2017}
}