In this paper, we introduce a novel deep-learning method to align cross-spectral images. Our approach relies on a learned descriptor which is invariant to different spectra. Multi-modal images of the same scene capture different signals and therefore their registration is challenging and it is not solved by classic approaches. To that end, we developed a feature-based approach that solves the visible (VIS) to Near-Infra-Red (NIR) registration problem. Our algorithm detects corners by Harris and matches them by a patch-metric learned on top of CIFAR-10 network descriptor. As our experiments demonstrate we achieve a high-quality alignment of cross-spectral images with a sub-pixel accuracy. Comparing to other existing methods, our approach is more accurate in the task of VIS to NIR registration.
@article{arxiv.1801.05171,
title = {Deep Multi-Spectral Registration Using Invariant Descriptor Learning},
author = {Nati Ofir and Shai Silberstein and Hila Levi and Dani Rozenbaum and Yosi Keller and Sharon Duvdevani Bar},
journal= {arXiv preprint arXiv:1801.05171},
year = {2021}
}