FGF-GAN: A Lightweight Generative Adversarial Network for Pansharpening via Fast Guided Filter

TL;DR

This paper introduces FGF-GAN, a lightweight generative adversarial network that uses a fast guided filter for improved pansharpening, achieving higher quality images with fewer parameters than existing methods.

Contribution

The paper proposes a novel FGF-GAN model that replaces traditional feature concatenation with fast guided filtering and incorporates spatial attention, enhancing pansharpening performance.

Findings

Outperforms existing methods in image quality.

Uses fewer parameters than comparable models.

Effectively preserves feature information through adversarial training.

Abstract

Pansharpening is a widely used image enhancement technique for remote sensing. Its principle is to fuse the input high-resolution single-channel panchromatic (PAN) image and low-resolution multi-spectral image and to obtain a high-resolution multi-spectral (HRMS) image. The existing deep learning pansharpening method has two shortcomings. First, features of two input images need to be concatenated along the channel dimension to reconstruct the HRMS image, which makes the importance of PAN images not prominent, and also leads to high computational cost. Second, the implicit information of features is difficult to extract through the manually designed loss function. To this end, we propose a generative adversarial network via the fast guided filter (FGF) for pansharpening. In generator, traditional channel concatenation is replaced by FGF to better retain the spatial information while reducing the number of parameters. Meanwhile, the fusion objects can be highlighted by the spatial attention module. In addition, the latent information of features can be preserved effectively through adversarial training. Numerous experiments illustrate that our network generates high-quality HRMS images that can surpass existing methods, and with fewer parameters.