The latest AI software by Nvidia turns rough doodles into realistic images. The prototype illustrates how AI is going to augment art.
AI is going to be huge for artists. The latest demonstration from Nvidia has built prototype software that turns doodles into realistic landscapes. It uses a type of AI model known as a generative adversarial network (GAN).
The software will instantly turn a couple of lines into a gorgeous mountaintop sunset. This is MS Paint for the AI age. The GauGAN shows what Nvidia’s neural network platforms can do. It’s designed to compile an image of how a human would paint. It can turn the sketch into a photorealistic photo in seconds.
The software gives users a smart paintbrush with which they can make a very basic outline of a scene before filling in their rough sketch with natural textures like grass and trees.
This technology isn’t new though; researchers have come up with similar ones in the past. Google also has one that turns doodles into clipart. However, this new Nvidia software is the most advanced one yet. It generates AI landscapes instantly and can predict where you are going with your doodle.
The company has not revealed if this would be turned into an actual software product. But it explains that the tools could help architects, urban planners, landscape designers and game developers in the future. The technology can convert sketches into very realistic images.
The new invention was revealed on Nvidia GTC 2019 earlier in the week. Nvidia Corporation is an American technology company based in California. It designs graphics processing units for the gaming and professional markets. It also provides chip units for the mobile computing and automotive market.