NVIDIA AI PLAYGROUND

NVIDIA AI Research in Action

AI and deep learning is serious business at NVIDIA, but that doesn’t mean you can’t have a ton of fun putting it to work. Researchers at NVIDIA challenge themselves each day to answer the “what ifs” that push deep learning architectures and algorithms to richer practical applications. See some of that work in these fun, intriguing, artful and surprising projects.

Image Inpainting

Image Inpainting

Step right up and see deep learning inference in action on your very own portraits or landscapes. Our researchers developed state-of-the-art image reconstruction that fills in missing parts of an image with new pixels that are generated from the trained model, independent from what’s missing in the photo. Give it a shot with a landscape or portrait. Erase at will — get rid of that photobomber, or your ex, and then see what happens when new pixels are painted into the holes.

View Research Paper > | Read More > | Resources >

Artistic Style Transfer

Artistic Style Transfer

Why spend years learning to paint like a cubist when deep learning can do the work in an instant? There’s a clever trick to quickly transferring the style of one photo onto another while keeping the resulting image photorealistic. NVIDIA researchers did it by adding stylization and smoothing steps to the transfer algorithm. Try it out and turn your favorite image into a Van Gogh, go for a cubist turn with Picasso, even see what you’d look like in a police sketch and more with this interactive style transfer algorithm.

View Research Paper > | Read More > | Resources >

Photorealistic Image Synthesis

Photorealistic Image Synthesis

Virtual worlds filled with scenes, people, and objects represent a real word challenge to generate with speed, resolution, realism, complexity and editability. Playing around with this synthesizer will give you a demonstration of the leading-edge approach our researchers took when it comes to generating faces. They engineered five new features into an existing network that now generates synthetic faces that are basically impossible to tell from “real” world images. Try it out and see if you can tell the difference.

View Research Paper > | Read More > | Resources >

JOIN OUR TEAM

Come solve the greatest challenges of our time.