Deep dual stream residual network with contextual attention for pansharpening of remote sensing images

TL;DR

This paper introduces a dual stream residual network with contextual attention for pansharpening remote sensing images, achieving superior quality by separately extracting features from multispectral and panchromatic images and effectively fusing them.

Contribution

It proposes a novel dual attention-based two-stream network that separately processes multispectral and panchromatic images for improved pansharpening performance.

Findings

Outperforms existing methods on Pleiades dataset

Achieves higher spectral and spatial fidelity

Demonstrates superior visual quality in results

Abstract

Pansharpening enhances spatial details of high spectral resolution multispectral images using features of high spatial resolution panchromatic image. There are a number of traditional pansharpening approaches but producing an image exhibiting high spectral and spatial fidelity is still an open problem. Recently, deep learning has been used to produce promising pansharpened images; however, most of these approaches apply similar treatment to both multispectral and panchromatic images by using the same network for feature extraction. In this work, we present present a novel dual attention-based two-stream network. It starts with feature extraction using two separate networks for both images, an encoder with attention mechanism to recalibrate the extracted features. This is followed by fusion of the features forming a compact representation fed into an image reconstruction network to produce a pansharpened image. The experimental results on the Pl\'{e}iades dataset using standard quantitative evaluation metrics and visual inspection demonstrates that the proposed approach performs better than other approaches in terms of pansharpened image quality.