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

Love podcasts or audiobooks? Learn on the go with our new app.

Get the Medium app

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
Andrey Nikishaev

Andrey Nikishaev

Machine Learning and Computer Vision Researcher. Founder LearnML.Today