We’ve often wondered while arena games or experiencing basic reality: how can this be closer to the real world? Nvidia might have an answer. The aggregation has developed an AI which can turn video into a basic landscape.

Nvidia has set up a demo zone at NeurIPS AI appointment in Montreal to show off this technology. The aggregation used its own supercomputer named the DGX-1, powered by Tensor Core GPUs to catechumen videos captured from a self-driving car’s dashcam. This setup made it accessible to covert theory into actual results.

The analysis team then extracted a high-level semantics map using a neural network, and then used Unreal Engine 4 to accomplish high-level colorized frames. In the last step, Nvidia uses its AI to catechumen these representations into images. Developers can edit the end result easily to suit their needs.

“Nvidia has been creating new ways to accomplish alternate cartoon for 25 years – and this is the first time we can do this with a neural network,” Vice President of Applied Deep Learning at Nvidia, Bryan Catanzaro, said in a statement. “Neural networks – accurately  – abundant models are going to change the way cartoon are created.”

He added that this technology will help developers and artists create basic agreeable at a much lower cost than before.

This is decidedly agitative for game developers and basic absoluteness agreeable creators as they can analyze new possibilities by cartoon from the accepted video. However, this technology is still in the development phase and requires a supercomputer. So we might have to wait a while until we see this on our consoles and desktops.

Read next: Microsoft is reportedly architecture a Chromium-based browser to alter Edge