90 Miles From Tyranny : Deep Fake Dilemna: Samsung taught the neural network to create facial animations in a single image. You can “revive” old pictures or pictures.

Friday, June 21, 2019

Deep Fake Dilemna: Samsung taught the neural network to create facial animations in a single image. You can “revive” old pictures or pictures.



Previously, this required much more input.


Researchers from the Samsung Center for the Study of AI Samsung have taught the neural network to create facial animation in a single image. To do this, we developed a new way to overlay personal landmarks: the system can make the “goal” speak, turn its head and apply facial expressions.


related: Man, the humans in this AI-created video look jaw-droppingly real


So far the result is not perfect, but realistic. This was achieved using a generative, adversary neural network, a type of neural networks consisting of two modules, one of which tries to deceive the other. Thus, the system constantly “learns” and produces a result with a...




Read More HERE

No comments:

Post a Comment