Related Articles
Artificial intelligence is now smart enough to paint in the missing regions of a face to fix a blink or turn a frown into a smile. But the problem is those A.I. programs use a strangers photograph, so while the programs may fix a bad blink, they also create a weird version of you with someone elses eyes. Facebook researchers, however, have come up with a solution by training an AI that uses your actual eyes from a previous photograph to fix that blink.Â
The tool uses a generative adversarial network, or GAN, which is a two part machine learning system whose dual components compete against each other to try to fool the system into thinking its computer generated images are real. Basically, one network is trained to recognize and classify whether images of open eyes are real, and the other network is trained to generate convincing images of open eyes. The generator network tries to create more and more convincing images to fool the classifier network, and the classifier network tries to get better at spotting these sophisticated fakes. Over time, each part of the GAN refines its skills and creates more accurate retouched images, as the network gets better at determining what realistic open eyes look like and how to successfully generate such images.
Facebook is already using machine learning to help identify faces on its platform and to give you tagging suggestions. And while the current technology is just in the research phase, it's a sign that the social network wants to maintain its dominance as a photo sharing platform. With more than 350 million photos uploaded to Platform.
Facebook isnt done researching the possibility of automatically fixing those blinking selfies, but with some additional work, a future version of the social network could do much more with automatic photo fixes before sharing.
