Experience AI in action from NVIDIA Research

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.

Sign up for notifications when new apps are added and get the latest NVIDIA Research news.



With NVIDIA GauGAN360, 3D artists can customize AI art for backgrounds with a simple web interface. Try the technology and see how AI can bring 360-degree images to life.



GauGAN2, named after post-Impressionist painter Paul Gauguin, creates photorealistic images from segmentation maps, which are labeled sketches that depict the layout of a scene.

Artists can use text, a paintbrush and paint bucket tools, or both methods to design their own landscapes. A style transfer algorithm allows creators to apply filters — changing a daytime scene to sunset, or a photorealistic image to a painting. Users can even upload their own filters to layer onto their masterpieces, or upload custom segmentation maps and landscape images as a foundation for their artwork

Read Blog >



Try writing song lyrics with a little help from AI and LyricStudio
Ready to discover the lyrics for your next hit song or need a few more lines to complete a favorite poem? See how AI can help you do just that!



Get lit like a pro with Lumos, an AI model that relights your portrait in video conference calls to blend in with the background. This high-quality deep learning model can adjust the lighting of the individual within the portrait based on the lighting in the background. It can even modify the glare of potential lighting on glasses! In this demonstration, you can interact with specific environments and see how lighting impacts the portraits.

Image Inpainting

NVIDIA 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 Story > | Resources >



To deploy speech-based applications globally, apps need to adapt and understand  any domain, industry, region and country specific jargon/phrases and respond naturally in real-time. See how NVIDIA® Riva helps you in developing world-class speech AI, customizable to your use case.

NVIDIA AI Playground GameGAN


Forty years since PAC-MAN first hit arcades in Japan, the retro classic has been reimagined, courtesy of artificial intelligence (AI). Trained on 50,000 episodes of the game, GameGAN, a powerful new AI model created by NVIDIA Research, can generate a fully functional version of PAC-MAN—this time without an underlying game engine. This means that even without understanding a game’s fundamental rules, AI can recreate the game with convincing results. It's the first neural network model that mimics a computer game engine by harnessing generative adversarial networks, or GANs.

PAC-MAN™&©BANDAI NAMCO Entertainment Inc

View Research Paper > | Watch Video > | Resources >

Art and Music in Light of AI

Explore the NVIDIA AI Art Gallery

Join Our Team

Come solve the greatest challenges of our time.