News for hackers. Stuff that matters.
Re:Google's New AI Photo Upscaling Tech Is Jaw-Dropping by actually_a_dog on Wednesday September 01, 2021 @01:48AM (#28376757)
How do you expect an algorithm to create information out of nowhere to fill in these details exactly as they were in the source photo?
Re:Google's New AI Photo Upscaling Tech Is Jaw-Dropping by nayaketo on Wednesday September 01, 2021 @02:24AM (#28376936)
If this AI can't produce upscaled photos that are close to original photos, the application of this tech is severely limited. There's not going to be CSI like "enhance" moment in real life like the article claims.
Re:Google's New AI Photo Upscaling Tech Is Jaw-Dropping by Jyaif on Wednesday September 01, 2021 @07:07AM (#28378357)
Have you heard of lossy compression? Are the application of lossy compression "severely limited"?
Re:Google's New AI Photo Upscaling Tech Is Jaw-Dropping by nayaketo on Wednesday September 01, 2021 @08:21AM (#28378915)
Meh! I'm sure there are use cases for this format but it ain't what this article claims it to be.
Re:Google's New AI Photo Upscaling Tech Is Jaw-Dropping by actually_a_dog on Wednesday September 01, 2021 @02:34AM (#28376980)
You really don't see any use for this if it can't create information? CSI "enhance" is, and always has been impossible.
Re:Google's New AI Photo Upscaling Tech Is Jaw-Dropping by nayaketo on Wednesday September 01, 2021 @08:16AM (#28378873)
It does create information though, just imaginary/wrong one.
Re:Google's New AI Photo Upscaling Tech Is Jaw-Dropping by actually_a_dog on Wednesday September 01, 2021 @08:27AM (#28378959)
No, it doesn't. A piece of code n bits long can only have a maximum of n bits of information in it; you can't get more than n bits of information out of it. It can't create information out of nothing.
Re:Google's New AI Photo Upscaling Tech Is Jaw-Dropping by ObscureScience on Wednesday September 01, 2021 @10:56AM (#28380604)
I'm not sure what you mean, but that is pretty much what generative neural systems do. If by information you mean data that correspond to reality? Than sure. I guess you can say that the data is a correlated to reality by a certain probability, and the better the model the higher the probability?
Re:Google's New AI Photo Upscaling Tech Is Jaw-Dropping by actually_a_dog on Wednesday September 01, 2021 @11:17AM (#28380924)
Information in the sense of information theory. You can't squeeze n+1 bits out of n bits of information.
Re:Google's New AI Photo Upscaling Tech Is Jaw-Dropping by webmaven on Wednesday September 01, 2021 @12:01PM (#28381531)
> You can't squeeze n+1 bits out of n bits of information.

Sure, in the extractive sense. But in the generative sense you can.

The fact that the extra information is 'synthetic' and not 'natural' doesn't mean that it isn't extra info, just that it may or may not (probably not) correspond with ground truth.

Another way to think of it is that super-resolution is effectively a (possibly benign) man-in-the-middle. If what you're concerned about is the information flowing from Alice to Bob, Eve isn't adding any info, and may in fact be drowning the signal in more noise. But you can also see it as Eve communicating more info to Bob than Alice is to Eve. Whether what Eve is adding should be considered noise or signal is highly context dependent.

Re:Google's New AI Photo Upscaling Tech Is Jaw-Dropping by actually_a_dog on Wednesday September 01, 2021 @12:05PM (#28381590)
Okay, then where does the information come from? A deterministic algorithm can't generate information where none exists.
Re:Google's New AI Photo Upscaling Tech Is Jaw-Dropping by webmaven on Wednesday September 01, 2021 @12:16PM (#28381796)
> A deterministic algorithm can't generate information where none exists.

Right. All the processes being used for these purposes are stochastic.

Edit: Actually they are deterministic, in the same way a pseudo-random-number-generator is, and typically rely on a 'seed' that would have to come from a random source to be non-deterministic, and doesn't, so users get to have pseudo-random but reproducible results. But that's really getting into the weeds.

Re:Google's New AI Photo Upscaling Tech Is Jaw-Dropping by omegalulw on Wednesday September 01, 2021 @03:13PM (#28384348)
Very simple, you _predict_. If you can tell the low res image is of a person's face, the likelihood of possibilities when filling in the blanks in the high res image are significantly reduced.