Nvidia just released a video showing off its use of a generative adversarial network (GAN) to create high-definition photos of fake humans. The results are impressive and extremely realistic as it uses a database of celebrity photos to generate new faces.
NVIDIA used a special “progressive” method that began the GAN’s tuition on low-res images, and then worked upwards to HD. “This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality” wrote the company of its approach.
This is another great example how powerful neural networks and AI really are and how they can be used for creative applications.
More information: research.nvidia.com