In a newsstory today in The Guardian and other medias it has been revealed that Google new Artificial Intelligence system is capable of “enhancing” an 8-pixel square image, increasing the resolution 16-fold and effectively restoring lost data.
In short: Google figured out a way to zoom and enhance photos just like in the movies.
A common trope in crime films and TV shows is the ability for law enforcement agencies to zoom in on grainy photos and security camera footage. But the more important news for graffiti artists: to ‘enhance‘ the pixelated image it’s no big deal anymore – making vandal squad work a breeze.
The fact is that it’s usually impossible to achieve this because there isn’t enough detail in a small number of pixels to eke out a clearer image than what you already have in the original file. But it looks like a bunch of Google researchers have figured out a way to do that – or at least get pretty darn close. But how?
In the image above, the images on the left show the 64 square pixel source images, while the ones in the middle show what Google Brain’s new system can construct from them. The rightmost column of images are higher resolution images from the source photos; you can compare it to the middle column to see just how accurate Google’s system is.
They came up with a pixel recursive super resolution model that can synthesize details in low-res photos by comibining the power of two neural networks.
„First, the conditioning network attempts to map the the 8×8 source image against similar high resolution images and approximates what the image might look like when zoomed in. Then, the prior network adds realistic details to the final output. It does this by learning what each pixel in a low-res sample generally corresponds to in high-res images.“
As you can see, the system is fairly competent. But: the tech isn’t nearly ready for prime-time, it could certainly come in handy in assisting police in solving crimes. Graffiti artists who plan to play any future role in one of the next graffiti movies, remember this article and how neural networks are getting closer to bringing sci-fi to life. The most safe way is still the diffuser/blur like in the screenshot below.