News for hackers. Stuff that matters.

A comment on Generative Adversarial Networks for Extreme Learned Image Compression. Parent comment

Re:Generative Adversarial Networks for Extreme Learned Image... by mcbits on Thursday April 12, 2018 @12:24AM (#16817967)
It could be a problem if it hallucinates the wrong license plate number at a crime scene. If all you want is a gigantic 8K resolution stock photo of a woman holding her baby in front of a laptop without devouring 10 MB of the user's data cap, it may be fine if the woman has a slightly different (but still highly detailed) hair style.
[ Parent | on HN ]
Re:Generative Adversarial Networks for Extreme Learned Image... by skybrian on Thursday April 12, 2018 @10:01AM (#16820981)
It would always decompress the same way, so for artistic purposes, if you preview it and it looks good, it is good.

But if you're using photography to look at things in the world, that's a whole different story.

[ Parent | on HN ]