The system was trained by being shown innumerable images of faces so that it learns typical facial features. A second portion of the system, meanwhile, focuses on comparing 8×8 pixel images with all the possible 32×32 pixel images they could be shrunken versions of.
The two networks working in harmony effectively redraw their best guess of what the original facial image would be.
The system allows for a huge improvement over old-fashioned methods of up-sampling, where an older system might simply look at a block of red in the middle of a face, make it 16 times bigger and blur the edges, Google’s system is capable of recognizing it is likely to be a pair of lips, and draw the image accordingly.
It should be noted however that the system is not capable of magic. While it can make educated guesses based on knowledge of what faces generally look like, it sometimes won’t have enough information to redraw a face that is recognizably the same person as the original image.
Sometimes, it just plain screws up, creating inhuman monstrosities. Nonetheless, the system works well enough to fool people around 10% of the time, for images of faces.
Running the same system on pictures of bedrooms is even better as test subjects were unable to correctly pick the original image almost 30% of the time. A score of 50% would indicate the system was creating images indistinguishable from reality.