SRGAN not the best thing for high resolution input, due to full size convolution. Only thing that how this can be processed multi-patch approach, when you process not full image but some regions and then combine them together, minimizing error on edges.

--

--

Machine Learning and Computer Vision Researcher. Founder LearnML.Today

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store