Remote Sensing Pan-Sharpening via Cross-Spectral–Spatial Fusion Network

Pan-sharpening is a technique used to create high-resolution multispectral (HRMS) images by merging low-resolution multispectral (LRMS) images with corresponding high-resolution panchromatic (PAN) images. Despite achieving state-of-the-art performance, existing panchromatic sharpening networks based on deep-learning (DL) methods suffer from spectral distortion and insufficient spatial texture enhancement. To address this challenge, this letter introduces a novel cross-spectral–spatial fusion network (CSSFN) for pan-sharpening remote sensing images. The network utilizes a cross-spectral–spatial attention block (CSSAB) to extract both the spectral information of the MS branch and the spatial information of the PAN branch. The spectral and spatial feature representations of remote sensing images are then progressively enhanced, which improves the fusion process and generates multispectral images with high spatial resolution. Our network outperforms other pan-sharpening methods on two publicly available datasets, as demonstrated by extensive experiments, yielding state-of-the-art results.

I. Introduction

High-resolution multispectral (HRMS) remote sensing images play a critical role in geographic information management and are widely used in various fields, including change detection [1], [2], scene classification [3], [4], environmental pollution monitoring [5], and land surveying [6]. However, due to the limitations of imaging equipment, satellites often capture low-resolution multispectral (LRMS) images and high-resolution panchromatic (PAN) images. Compared to MS images, PAN images have the characteristics of high spatial resolution and a single band. To obtain HRMS images, researchers employ pan-sharpening technology to merge the spectral information of LRMS images with the spatial information of PAN images. As a result, the pan-sharpening algorithm is a crucial fusion technology for remote sensing images in practical applications.