Think fake news is bad? Just wait for the fake video that starts a war – the terrifying truth about AI, algorithms and avatars
From a single selfie, new technology can create a moving, talking avatar. Soon it could be a smartphone app. It could come in handy if you have to skip a video call, but what of the fake North Korea video announcing a missile attack?
All it takes is a single selfie.
From that static image, an algorithm can quickly create a moving, lifelike avatar: a video not recorded, but fabricated from whole cloth by software.
With more time, Pinscreen, the Los Angeles start-up behind the technology, believes its renderings will become so accurate they will defy reality.
“You won’t be able to tell,” said Hao Li, a leading researcher on computer-generated video at the University of Southern California who founded Pinscreen in 2015. “With further deep-learning advancements, especially on mobile devices, we’ll be able to produce completely photo-real avatars in real time.”
The technology is a triumph of computer science that highlights the gains researchers have made in deep neural networks, complex algorithms that loosely mimic the thinking of the human brain.
Similar breakthroughs in artificial intelligence allowed University of Washington researchers to move US President Barack Obama’s mouth to match a made-up script and the chip maker Nvidia to train computers to imagine what roads would look like in different weather.