# Deep Multi-Spectral Registration Using Invariant Descriptor Learning

arXiv: https://arxiv.org/abs/1801.05171 · HTML: https://mlsanity.com/paper/1801.05171/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jan 2018.

## Built on by (most cited first, 6 of 6)

- [Relational Representation Learning Network for Cross-Spectral Image Patch Matching](https://mlsanity.com/paper/2403.11751/) (2024)
- [Why and How: Knowledge-Guided Learning for Cross-Spectral Image Patch Matching](https://mlsanity.com/paper/2412.11161/) (2024)
- [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)
- [Attention-Based Multimodal Image Matching](https://mlsanity.com/paper/2103.11247/) (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 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.