# Registration and Fusion of Multi-Spectral Images Using a Novel Edge Descriptor

arXiv: https://arxiv.org/abs/1711.01543 · HTML: https://mlsanity.com/paper/1711.01543/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2017.

## Built on by (most cited first, 3 of 3)

- [Classic versus deep learning approaches to address computer vision challenges](https://mlsanity.com/paper/2101.09744/) (2021)
- [Multispectral image fusion based on super pixel segmentation](https://mlsanity.com/paper/2112.11329/) (2021)
- [Visible and infrared self-supervised fusion trained on a single example](https://mlsanity.com/paper/2307.04100/) (2023)

## Abstract (arXiv)

In this paper we introduce a fully end-to-end approach for multi-spectral image registration and fusion. Our method for fusion combines images from different spectral channels into a single fused image by different approaches for low and high frequency signals. A prerequisite of fusion is a stage of geometric alignment between the spectral bands, commonly referred to as registration. Unfortunately, common methods for image registration of a single spectral channel do not yield reasonable results on images from different modalities. For that end, we introduce a new algorithm for multi-spectral image registration, based on a novel edge descriptor of feature points. Our method achieves an accurate alignment of a level that allows us to further fuse the images. As our experiments show, we produce a high quality of multi-spectral image registration and fusion under many challenging scenarios.