On Friday, Adobe shared its collaboration with UC Berkeley scientists that applies machine learning. Adobe researchers collaborated with colleagues from UC Berkeley to train a neural network on a set of before and after face images that had been automatically warped using the Face Aware Liquify tool, as well as a set of headshots that had been edited by an actual artist using the same tool. “Fake content is a serious and increasingly pressing issue,” Adobe said. To create the software, engineers trained a neural network on a database of paired faces, containing images both before and after they’d been edited using Liquify.
The resulting algorithm is impressively effective. The tool is even able to suggest how to restore a photo to its original, unedited appearance. “The idea of a magic universal ‘undo’ button to revert image edits is still far from reality,” Adobe researcher Richard Zhang said. Those are promising results, but the neural network has a long way to go before it could be unleashed upon the billions of photos floating around the internet right now.