Google's Enhance AI - Super Resolution Is Here! 🔍

📝 The paper "Image Super-Resolution via Iterative Refinement " is available here:

🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Aleksandr Mashrabov, Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bryan Learn, Christian Ahlin, Eric Martel, Gordon Child, Ivo Galic, Jace O'Brien, Javier Bustamante, John Le, Jonas, Kenneth Davis, Klaus Busse, Lorin Atzberger, Lukas Biewald, Matthew Allen Fisher, Mark Oates, Michael Albrecht, Michael Tedder, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Rajarshi Nigam, Ramsey Elbasheer, Steef, Taras Bobrovytsky, Thomas Krcmar, Timothy Sum Hon Mun, Torsten Reil, Tybie Fitzhugh, Ueli Gallizzi.

Károly Zsolnai-Fehér's links:

[adamgotya]

ah yes, the age of yelling "ENHANCE" at a dude on a computer is almost here

[EpicVideos]

47.4% is even more impressive when you consider the maximum is 50% not 100% as, if you put two real images next to each other, you'd expect each to be equally likely to be picked.

[RBlnd]

What I've always wanted to do with super resolution is zoom in to some image, enhance it, then repeat the process over and over and see what kind of weird stuff happens

[julinaut]

3:40 I think it's worth to note here that 50% would be the perfect score. Because if people couldn't tell the difference at all, they would most likely choose randomly, resulting in them choosing the real one 50% of the time on average. So 47.4% is A LOT better than it sounds. Truly amazing. What a time to be alive indeed!

[neillunavat]

The previous paper is literally what inspired me to start learning programming and machine learning! I love this stuff.

[yqisq]

Just a note of caution: the AI essentially becomes an artist who fills in the gaps by imagination - the result shouldn't be interpreted as recovering reality from noisy data.

[leonlazic]

These are some really crazy results. But I have on observation that might be interesting to some. I can easily tell which ones were upscaled as long as they were showing their teeth. I am a dental technician focused on facial esthetics and these upscaled images all have very bad/impossible tooth positions and esthetics. The problem with teeth is that they serve very specific and complex functions (chewing and phonetics). The upscaling AI of course does not compute the jaw movements and is not aware that their position affects both eating and speaking. A trained eye like mine can easily spot the errors in the first 10s of looking at the photo. There are issues like midline shift and inclination, incorrect gingival zenith heights, incorrect incisor lenghts, gummy smile, teeth not following the lipline ... Don't get me wrong these esthetic issues are present in real humans as well, but are definitely not that common as in every picture here.
This is just a constructive critisism and the results are still awesome and I am a believer that these issues will be fixed two papers down the line ;)

[PrinceWesterburg]

That'd be fun to put pixel art into or just anything to see what it created

[enquiryplay]

CSI was just ahead of its time with the "zoom and enhance" technique.

[RasmusSchultz]

"Super resolution", but it appears this does faces only? If so, it's more like face synthesis, like NVidia have been doing for a while, and they've already done something similar with that model. Not that this doesn't have interesting applications. But it's not general super resolution, is it? It's more like the 64x64 pixels are input parameters - configuration for a face synthesizer.

[thomaslao]

is there an executable for this? I want to try it out.

[frothydv]

Really looking forward to the day when this is applied to old PC games. Feels like there's so much potential to have AI "enhance" old grainy games and give them new life. Even modern games could benefit. So many amazing games from the early 90s that would likely work well.

[DreckbobBratpfanne]

Once this reliable this would be one hell of a compression method.
Imagine scaling down an HD image to 64x64 pixels (and then compress those as well). The amount of storage save would be gigantic

[Mopsie]

We need old 90s shows remastered with this

[DamianReloaded]

I really wanna play 1993 X-COM: UFO Defense in super resolution. I'm intrigued to find out what kind of artwork machine learning could generate while upscaling old games. I imagine one way to train it would be to down-scale high resolution footage of modern video games and use that as input and the original HD footage as the expected value.

[wqmwxzj]

What's cooler is that there are at least like 5 major companies that I know of with their own versions of this that they're working on and improving.

[otm]

What a joy it'll be when State prosecutors get a hold of and misapply this technology.

[animaToy]

Now I'm curious how this method can handle compressed images. As far as I can see all the examples where pixelated, but not compressed and I think compressed material may be a bit tougher than just pixelated image. On pixelated images data frequency is still proportional to the source material, but compression algorithms can change frequency of details, so my question is, how good this method is with irregular detail frequency on compressed images like heavily compressed, low resolution jpegs?

[HappyBirthdayGreetings]

Denoising is only going to get better and rendering speed will reduce considerably

[MushookieMan]

"It can even deal with glasses" *Shows a man with hovering glasses.*