Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural network

TL;DR

This paper presents a deep neural network that super-resolves Sentinel-2 satellite images from 20m and 60m to 10m resolution, trained globally to generalize across diverse geographic and land-cover types, outperforming existing methods.

Contribution

The authors develop a globally trained CNN for Sentinel-2 super-resolution that generalizes across different regions without retraining, achieving significant accuracy improvements.

Findings

Outperforms previous methods by nearly 50% in RMSE.

Provides visually convincing 10m resolution images.

Generalizes well across various geographic and land-cover types.

Abstract

The Sentinel-2 satellite mission delivers multi-spectral imagery with 13 spectral bands, acquired at three different spatial resolutions. The aim of this research is to super-resolve the lower-resolution (20 m and 60 m Ground Sampling Distance - GSD) bands to 10 m GSD, so as to obtain a complete data cube at the maximal sensor resolution. We employ a state-of-the-art convolutional neural network (CNN) to perform end-to-end upsampling, which is trained with data at lower resolution, i.e., from 40->20 m, respectively 360->60 m GSD. In this way, one has access to a virtually infinite amount of training data, by downsampling real Sentinel-2 images. We use data sampled globally over a wide range of geographical locations, to obtain a network that generalises across different climate zones and land-cover types, and can super-resolve arbitrary Sentinel-2 images without the need of retraining. In quantitative evaluations (at lower scale, where ground truth is available), our network, which we call DSen2, outperforms the best competing approach by almost 50% in RMSE, while better preserving the spectral characteristics. It also delivers visually convincing results at the full 10 m GSD. The code is available at https://github.com/lanha/DSen2