NVIDIA’s new AI breakthrough uses conditional generative neural network as a starting point to train a neural network to render new 3D environments, after being trained on existing videos. This enables developers and artists to create new interactive 3D virtual worlds for automotive, gaming or virtual reality by training models on videos from the real world, thus lowering the cost as well as time it takes to create virtual worlds. Read more to see it in-action and for additional information.
This tech demo is made possible by NVIDIA Tensor Core GPUs, and the research is currently on display at the NeurIPS conference in Montreal, Canada, a show attended by the world’s most prominent artificial intelligence researchers. More specifically, the research team created a simple driving game for NeurIPS which allows attendees to interactively navigate an AI-generated environment.
“Neural networks – specifically – generative models are going to change the way graphics are created. One of the main obstacles developers face when creating virtual worlds, whether for game development, telepresence, or other applications is that creating the content is expensive. This method allows artists and developers to create at a much lower cost, by using AI that learns from the real world,” said Bryan Catanzaro, Vice President of Applied Deep Learning at NVIDIA.