Towards Streamlined Single-Image Super-Resolution: Demonstration with 10 m Sentinel-2 Colour and 10–60 m Multi-Spectral VNIR and SWIR Bands

Higher spatial resolution imaging data are considered desirable in many Earth observation applications. In this work, we propose and demonstrate the TARSGAN (learning Terrestrial image deblurring using Adaptive weighted dense Residual Super-resolution Generative Adversarial Network) system for Restoration (SRR) of 10 m/pixel Sentinel-2 “true” colour images as well all other multispectral bands. parallel, ELF (automated Edge detection measurements edge spread function, Line Full width at half maximum) is proposed to achieve automated precise assessments effective resolutions input SRR images. Subsequent results suggest an averaged enhancement factor about 2.91 times (equivalent ~3.44 bands) given a nominal upscaling 4 times. Several examples provided different types scenes from urban landscapes agricultural sea-ice floes.