The eyes don't have it! AI's 'deep-fake' vids surge ahead in realism

Videos Using AI to make fake videos look as realistic as possible is all the rage at the moment. Developers aren't deterred by the controversy surrounding deepfakes – videos in which people's faces are digitally pasted onto the bodies of smut stars and other performers using machine-learning software. OK, sure, adding Nicholas Cage's face randomly into movie scenes is pretty funny. Despite all this, many are still pushing for new algorithms that create fake videos that are even more lifelike. Researchers from Carnegie Mellon University and Facebook Reality Lab are presenting Recycle-GAN, a generative adversarial system for "unsupervised video retargeting" this week at the European Conference on Computer Vision (ECCV) in Germany.