Deep Multi-Spectral Registration Using Invariant Descriptor Learning
This addresses a challenging multi-modal image registration problem for applications like remote sensing or medical imaging, but it is incremental as it builds on existing feature-based and deep-learning techniques.
The paper tackles the problem of aligning cross-spectral images, specifically visible to near-infrared registration, by introducing a deep-learning method that uses a learned invariant descriptor, achieving sub-pixel accuracy and outperforming existing methods.
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.