Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation

TL;DR

This paper introduces a multi-spectral multi-image super-resolution method for Sentinel-2 imagery, enhancing image quality and building delineation accuracy by incorporating radiometric consistency losses, using a new dataset based on PlanetScope and Sentinel-2 data.

Contribution

The paper presents the first application of multi-image super-resolution to multi-spectral remote sensing imagery with a radiometric consistency module, improving fidelity and downstream building delineation.

Findings

MISR outperforms single-image super-resolution on fidelity metrics.

Radiometric consistency improves preservation of sensor radiometric properties.

Multi-image super-resolution enhances building delineation accuracy.

Abstract

High resolution remote sensing imagery is used in broad range of tasks, including detection and classification of objects. High-resolution imagery is however expensive, while lower resolution imagery is often freely available and can be used by the public for range of social good applications. To that end, we curate a multi-spectral multi-image super-resolution dataset, using PlanetScope imagery from the SpaceNet 7 challenge as the high resolution reference and multiple Sentinel-2 revisits of the same imagery as the low-resolution imagery. We present the first results of applying multi-image super-resolution (MISR) to multi-spectral remote sensing imagery. We, additionally, introduce a radiometric consistency module into MISR model the to preserve the high radiometric resolution of the Sentinel-2 sensor. We show that MISR is superior to single-image super-resolution and other baselines on a range of image fidelity metrics. Furthermore, we conduct the first assessment of the utility of multi-image super-resolution on building delineation, showing that utilising multiple images results in better performance in these downstream tasks.