Nvidia is putting more effort to research & develope AI and deep learning, and recently we've seen the video showing its AI can creates beautiful landscape images from simple sketches( watch video below). Today they have just made it publish beta under the name GauGAN. The AI named after post-Impressionist painter Paul Gauguin, creates photorealistic images from segmentation maps, which are labeled sketches that depict the layout of a scene.GauGan turns rough doodles into highly realistic scenes using generative adversarial networks (GANs). Dubbed GauGAN, the tool is like a smart paintbrush, converting segmentation maps into lifelike images
You can Try GauGAN beta. Here are few images that we've tried
The AI does very good job although we can see some bug or title (repeated) area on the auto-generated image but it looks promissing. There is not much information about next release but according to sneak Peek information that Nvidia will release this as a program for Windows with hires later this year. Stay tuned !
[post_ads_2]