Paired Google networks are part of a newly revealed AI system capable of increasing the resolution of blurred or pixelated faces in a way previously thought impossible. The system is composed of two networks working together to redraw their best guess of what the original facial image would be. One system views vast numbers of facial images to learn typical facial features. A second system compares 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.