An Approach to Super-Resolution of Sentinel-2 Images Based on Generative Adversarial Networks

TL;DR

This paper introduces S2GAN, a generative adversarial network-based method to enhance Sentinel-2 image resolution, achieving superior results over traditional and deep learning methods through a two-step process involving super-resolution and discrimination.

Contribution

The paper proposes a novel GAN-based super-resolution approach specifically designed for Sentinel-2 images, utilizing residual connections and a two-step training process for improved spatial resolution enhancement.

Findings

S2GAN outperforms conventional SR methods in experiments.

The approach effectively enhances 20m and 60m bands using 10m bands as guidance.

Experimental results demonstrate the method's superiority in realism and accuracy.

Abstract

This paper presents a generative adversarial network based super-resolution (SR) approach (which is called as S2GAN) to enhance the spatial resolution of Sentinel-2 spectral bands. The proposed approach consists of two main steps. The first step aims to increase the spatial resolution of the bands with 20m and 60m spatial resolutions by the scaling factors of 2 and 6, respectively. To this end, we introduce a generator network that performs SR on the lower resolution bands with the guidance of the bands associated to 10m spatial resolution by utilizing the convolutional layers with residual connections and a long skip-connection between inputs and outputs. The second step aims to distinguish SR bands from their ground truth bands. This is achieved by the proposed discriminator network, which alternately characterizes the high level features of the two sets of bands and applying binary classification on the extracted features. Then, we formulate the adversarial learning of the generator and discriminator networks as a min-max game. In this learning procedure, the generator aims to produce realistic SR bands as much as possible so that the discriminator incorrectly classifies SR bands. Experimental results obtained on different Sentinel-2 images show the effectiveness of the proposed approach compared to both conventional and deep learning based SR approaches.