Neural Enhance – Super Resolution for images using deep learning

Re:Neural Enhance – Super Resolution for images using deep l... by thenomad on Saturday October 29, 2016 @06:14AM (#12823373)

This looks amazing.

Question for the more experienced deep learning folk: if I wanted to use this to upscale textures for a game, would I have to train it on the same type of texture? In other words additional wood textures when upscaling wood, brick when upscaling brick textures, and so on?

[ Parent | on HN ]

Re:Neural Enhance – Super Resolution for images using deep l... by nuclai on Saturday October 29, 2016 @12:10PM (#12824586)

(Author here.) If you have the luxury to train on domain-specific textures, the results will definitely be better. That's why I included all the training code in the repository as well—to allow for this kind of solution.

If you scroll down on GitHub to see the faces examples, those are achieved by a domain-specific network. I suspect you'll similarly get extremely high-quality if you have good input images.

[ Parent | on HN ]

Re:Neural Enhance – Super Resolution for images using deep l... by martinkallstrom on Saturday October 29, 2016 @06:47AM (#12823426)

Yes, that would help a lot with output quality. The machine can only hallucinate what it has previously seen.

[ Parent | on HN ]