Boosting the accuracy of multi-spectral image pan-sharpening by learning a deep residual network

TL;DR

This paper introduces a very deep residual neural network for multi-spectral image pan-sharpening, significantly improving fusion accuracy over traditional shallow models through residual learning.

Contribution

The paper proposes a deep residual network architecture for pan-sharpening, leveraging residual learning to enhance performance beyond existing shallow neural network models.

Findings

Outperforms mainstream algorithms in accuracy

Achieves highest spatial-spectral fusion quality

Validated on diverse high-quality multi-spectral images

Abstract

In the field of fusing multi-spectral and panchromatic images (Pan-sharpening), the impressive effectiveness of deep neural networks has been recently employed to overcome the drawbacks of traditional linear models and boost the fusing accuracy. However, to the best of our knowledge, existing research works are mainly based on simple and flat networks with relatively shallow architecture, which severely limited their performances. In this paper, the concept of residual learning has been introduced to form a very deep convolutional neural network to make a full use of the high non-linearity of deep learning models. By both quantitative and visual assessments on a large number of high quality multi-spectral images from various sources, it has been supported that our proposed model is superior to all mainstream algorithms included in the comparison, and achieved the highest spatial-spectral unified accuracy.