News for hackers. Stuff that matters.
Re:Generative Adversarial Networks for Extreme Learned Image... by iTokio on Wednesday April 11, 2018 @06:58PM (#16816533)
The trick is not so much about compression, but rather about image generation. The trade off is completely different from usual lossy algorithms. A highly compressed image might still retain high visual quality but with completely different details, textures.

Kinda what would happen if you use a perfect painter with a blurry memory.

Re:Generative Adversarial Networks for Extreme Learned Image... by Tossrock on Wednesday April 11, 2018 @07:31PM (#16816765)
This is quite visible in their demonstration slider-image; the building in the back-right changes from a brick building with glass windows to a stucco-ish building with a bunch of exterior duct-work.
Re:Generative Adversarial Networks for Extreme Learned Image... by fludlight on Wednesday April 11, 2018 @08:09PM (#16816954)
Also, the car behind the bus disappears. It looks like it's been photoshopped out. This is unexpected behavior from a compression algorithm. Users are conditioned to expect the quality to degrade uniformly across the whole image.
Re:Generative Adversarial Networks for Extreme Learned Image... by Veedrac on Wednesday April 11, 2018 @09:14PM (#16817260)
In fairness that detail isn't preserved in the other formats either. The new issue is merely the illusion of accuracy.
Re:Generative Adversarial Networks for Extreme Learned Image... by rasz on Wednesday April 11, 2018 @09:50PM (#16817383)
car is visible in WebP.
Re:Generative Adversarial Networks for Extreme Learned Image... by w_t_payne on Wednesday April 11, 2018 @08:18PM (#16817009)
You would have to be very very careful indeed if you wanted to use this for anything with safety implications.
Re:Generative Adversarial Networks for Extreme Learned Image... by frenchie4111 on Wednesday April 11, 2018 @07:42PM (#16816816)
This would have interesting implications if we accidentally trained biased networks (provocative example: improperly changing people's skin-colors in images when decoding them)