Generative Adversarial Networks for Extreme Learned Image Compression

Post by skybrian » Thu, Apr 12, 2018, 2:01 PM UTC

mcbits wrote: post #21

skybrian wrote: post #18

Earlier quoted context omitted.

Okay, but still, some kinds of changes are better than others. They should probably start testing for this in the visual perception tests: is lost information greyed out in a visible way? Are words and digits always fuzzed, or replaced? Because it turns out that fuzziness and compression artifacts have a higher-level meaning: when you see them, you know something has been lost. That's an important (if inadvertent) si…

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.

Post by rasz » Fri, Apr 13, 2018, 7:16 PM UTC

yorwba wrote: post #17

rasz wrote: post #15

Picture is not compressed, its hallucinated from vague memory of the real thing, a mere dream. Cars vanish, building change wall structure, even the license plate receives fake text absent from source materia. Its a giant guesswork of what was there originally. Reminds me of Xerox scanners lying about scanned in numbers http://www.dkriesel.com/en/blog/2013/0802_xerox-workcentres_...

All lossy compression algorithms hallucinate. That's the whole point: reducing image size by dropping some information and then hallucinating a plausible replacement to decompress. The only difference is that this compression is better at hallucinating, so you don't get ringing artifacts or blocks, but some internally consistent alternate reality. If you don't want to lose data you should not use lossy compression at…