There and Back Again: Self-supervised Multispectral Correspondence Estimation
This addresses the challenge of aligning multi-spectral images for applications like autonomous vehicles and medical imaging, offering a generalizable framework that is incremental over existing cross-spectral techniques.
The paper tackles the problem of dense correspondence estimation between different spectra (e.g., RGB-FIR, RGB-NIR) by introducing a self-supervised method with a novel cycle-consistency metric and spectra-agnostic loss functions, achieving higher accuracy than similar self-supervised approaches.
Across a wide range of applications, from autonomous vehicles to medical imaging, multi-spectral images provide an opportunity to extract additional information not present in color images. One of the most important steps in making this information readily available is the accurate estimation of dense correspondences between different spectra. Due to the nature of cross-spectral images, most correspondence solving techniques for the visual domain are simply not applicable. Furthermore, most cross-spectral techniques utilize spectra-specific characteristics to perform the alignment. In this work, we aim to address the dense correspondence estimation problem in a way that generalizes to more than one spectrum. We do this by introducing a novel cycle-consistency metric that allows us to self-supervise. This, combined with our spectra-agnostic loss functions, allows us to train the same network across multiple spectra. We demonstrate our approach on the challenging task of dense RGB-FIR correspondence estimation. We also show the performance of our unmodified network on the cases of RGB-NIR and RGB-RGB, where we achieve higher accuracy than similar self-supervised approaches. Our work shows that cross-spectral correspondence estimation can be solved in a common framework that learns to generalize alignment across spectra.