SDRCNN: A single-scale dense residual connected convolutional neural network for pansharpening

TL;DR

This paper introduces SDRCNN, a lightweight single-scale dense residual CNN for pansharpening, which outperforms traditional and deep learning methods in accuracy, spectral fidelity, and efficiency across multiple satellite datasets.

Contribution

The study proposes a novel dense residual connected CNN architecture for pansharpening, achieving a better accuracy-efficiency balance than existing methods.

Findings

SDRCNN produces less spatial and spectral distortion.

It has the shortest processing time among tested methods.

Ablation experiments confirm the effectiveness of each component.

Abstract

Pansharpening is a process of fusing a high spatial resolution panchromatic image and a low spatial resolution multispectral image to create a high-resolution multispectral image. A novel single-branch, single-scale lightweight convolutional neural network, named SDRCNN, is developed in this study. By using a novel dense residual connected structure and convolution block, SDRCNN achieved a better trade-off between accuracy and efficiency. The performance of SDRCNN was tested using four datasets from the WorldView-3, WorldView-2 and QuickBird satellites. The compared methods include eight traditional methods (i.e., GS, GSA, PRACS, BDSD, SFIM, GLP-CBD, CDIF and LRTCFPan) and five lightweight deep learning methods (i.e., PNN, PanNet, BayesianNet, DMDNet and FusionNet). Based on a visual inspection of the pansharpened images created and the associated absolute residual maps, SDRCNN exhibited least spatial detail blurring and spectral distortion, amongst all the methods considered. The values of the quantitative evaluation metrics were closest to their ideal values when SDRCNN was used. The processing time of SDRCNN was also the shortest among all methods tested. Finally, the effectiveness of each component in the SDRCNN was demonstrated in ablation experiments. All of these confirmed the superiority of SDRCNN.