Super-Resolution Restoration of Spaceborne Ultra-High-Resolution Images Using the UCL OpTiGAN System

We introduce a robust and light-weight multi-image super-resolution restoration (SRR) method processing system, called OpTiGAN, using combination of maximum posteriori approach deep learning approach. show the advantages combined two-stage SRR scheme for significantly reducing inference artefacts improving effective resolution in comparison to other techniques. demonstrate optimality OpTiGAN ultra-high-resolution satellite images video frames from 31 cm/pixel WorldView-3, 75 Deimos-2 70 SkySat. Detailed qualitative quantitative assessments are provided results on CEOS-WGCV-IVOS geo-calibration validation site at Baotou, China, which features artificial permanent optical targets. Our measurements have shown 3.69 times enhancement WorldView-3 imagery 9 SRR.