The result is the ability to render photorealistic faces of "unprecedented quality." How NVIDIA achieves this is by using an algorithm that pairs two neural networks—a generator and a ...

NVIDIA notes in a recently released research paper (PDF), "We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator ...

Today at SIGGRAPH 2023, Nvidia announced a new partnership with Hugging Face Inc., a company that develops tools for machine learning and AI, that will allow developers to deploy and use their ...

Over at Nvidia, Tero Karras, Samuli Laine, and Timo Aila published a paper (and accompanying video, viewable above) showing off what their AI is capable of when generating human faces.

Nvidia has just about pulled off the trick of rendering computer-generated human faces — in real time — that won’t make viewers squirm. At least so long as they don’t grimace. Or try to talk.

One set of algorithms (a generator) tries to create something – in this case a human face – while another set (a judge) tries to determine if it’s a real image or a fake one.