News for hackers. Stuff that matters.
Re:Generative Adversarial Networks for Extreme Learned Image... by FrozenVoid on Thursday April 12, 2018 @07:10AM (#16819632)
For photo quality material this will be a detail loss, but some media(animation/clip art/compressed video) can benefit greatly if the algorithm of reconstruction is fast enough. They should compare it with AV1/x265 codecs.

There are no comments on this comment yet.