Researchers have developed an AI tool that can turn blurry, unrecognizable pictures of people’s faces into eerily convincing computer-generated portraits, in finer detail than ever before. Previous methods can scale an image of a face up to eight times its original resolution. The new system, called PULSE, takes a handful of pixels and creates realistic-looking faces with up to 64 times the resolution, “imagining” features such as fine lines, eyelashes, and stubble that weren’t there in the first place.
The system cannot be used to identify people; it won’t turn an out-of-focus, unrecognizable photo from a security camera into a crystal-clear image of a real person. Rather, it is capable of generating new faces that don’t exist but look plausibly real.
While the researchers focused on faces as a proof of concept, the same technique could in theory take low-res shots of almost anything and create sharp, realistic looking pictures, with applications ranging from medicine and microscopy to astronomy and satellite imagery.
Traditional approaches take a low-resolution image and guess what extra pixels are needed by trying to get them to match, on average, with corresponding pixels in high-resolution images the computer has seen before. As a result of this averaging, textured areas in hair and skin that might not line up perfectly from one pixel to the next end up looking fuzzy and indistinct. Instead of taking a low-resolution image and slowly adding new detail, PULSE scours AI-generated examples of high-resolution faces, searching for ones that look as much as possible like the input image when shrunk down to the same size.
The team used a tool in machine learning called a “generative adversarial network” (GAN) — two neural networks trained on the same dataset of photos. One network comes up with AI-created human faces that mimic the ones it was trained on, while the other takes this output and decides if it is convincing enough to be mistaken for the real thing. The first network gets better with experience until the second network can’t tell the difference.
PULSE can create realistic looking images from noisy, poor-quality input that other methods can’t. From a single blurred image of a face, it can spit out any number of uncannily lifelike possibilities, each of which looks subtly like a different person. Even given pixelated photos where the eyes and mouth are barely recognizable, the algorithm manages to do something with it — something traditional approaches can’t do.
The system can convert a 16 × 16-pixel image of a face to 1024 × 1024 pixels in a few seconds, adding more than a million pixels — akin to HD resolution. Details such as pores, wrinkles, and wisps of hair that are imperceptible in the lowres photos become crisp and clear in the computer-generated versions.