Graphics chip maker Nvidia uses neural networks to draw photo-realistic images.
These aren't real people!
Can you believe what you see? Thanks to Nvidia , that may no longer be the case.
The graphics chip maker published a study last week on its use of "generative adversarial networks," or a kind of artificial intelligence that employs two neural networks, to create photo-realistic images of fake celebrities. See those photos above? Those aren't real people.
The process begins with a low-resolution image, and the two neural networks work to lay out more high-definition features until you get to those finished results. The company used the CelebA database of stock celebrity images to create different mash-ups.
AI is one of the hottest trends in the tech world, with companies like Google, Apple and Amazon using artificial intelligence to let your phone recognize real-world objects, help you better run your smart home or find that right photo in your camera roll.