Many people have fond memories of using the Game Boy Camera, but to call its low-resolution black-and-white shots "photos" would be... generous. Don't tell that to Roland Meertens, though. He recently devised a neural network that turns Game Boy Camera images into more presentable pictures. He trained the AI to clean up, colorize and fill in details for images by feeding it thousands of photos reduced to Game Boy-level image quality. The results aren't exactly good enough to frame for posterity, but they're far easier on the eyes.
As is, this is strictly a novelty. It's hard just to find a Game Boy Camera, let alone the companion printer you'll likely need to get images off the system. It's also focused on faces where everything is clearly visible, and has trouble with sideways glances, sunglasses and other However, it isn't hard to see the technology applying to other instances where AI can improve image quality. This could help identify a suspect from grainy security camera footage, for instance, or restore damaged photos. However it's used, it's a testament to how far imaging tech has come since the Game Boy Camera's 1998 debut.