Simulation / Modeling / Design

NVIDIA’s GauGAN Wins a 2019 Popular Science “Best of What’s New Award”

NVIDIA’s viral real-time AI art sensation GauGan just won a “Best of What’s New Award” in the engineering category, Popular Science magazine announced today.

“The Best of What’s New is our celebration of the most impactful and exciting innovations of the year,” says Popular Science Editor-in-Chief Joe Brown. “This expertly vetted collection lays the groundwork for a healthier, safer, and awe-inspiring future—in our homes, cities, outer space, and everywhere in between. We’re proud to bring you the Best of What’s New 2019.”

Developed by NVIDIA and UC Berkeley researchers in early 2019, GauGAN is the first semantic image synthesis model that can produce complex and lifelike images with only a few brushstrokes. 

“It’s much easier to brainstorm designs with simple sketches, and this technology is able to convert sketches into highly realistic images,” said Bryan Catanzaro, vice president of applied deep learning research at NVIDIA.

On the back-end, GauGan is based on a generative adversarial network (GAN) and trained on over one million real landscape images, using an NVIDIA DGX-1 system, with the cuDNN-accelerated PyTorch deep learning framework.

To date, over a million images have been created using GauGan on NVIDIA’s AI Playground.

“This technology is not just stitching together pieces of other images, or cutting and pasting textures,” Catanzaro said. “It’s actually synthesizing new images, very similar to how an artist would draw something.”

The NVIDIA Research team consists of more than 200 scientists around the globe, focusing on areas including AI, computer vision, self-driving cars, robotics and graphics.

Read more>

Discuss (0)

Tags