Chip designer Nvidia is teaching A.I. to build realistic 3D environments from short video clips.
The method builds on previous research on generative adversarial networks (GANs). Nvidia’s system generated graphics taken from open-source data sets used by the autonomous driving field. Using short clips segmented into various categories (buildings, sky, vehicles, signs, trees, people) the GAN was trained to generate new, different versions of these objects.
Future applications of automatically-generated virtual environments are vast: think training environments for logistics (warehouses, factories, shipping centers), urban planning simulations, even testing customer flow scenarios within amusement parks and shopping centers.
This trend is part of our section on Artificial Intelligence. Other trends in this section include:
Advertising and Public Relations, Book Publishers, Broadcasters, Radio and TV, Cable & Satellite TV Production & Distribution, Casinos/Gambling, Civil Servants/Public Officials, Clergy & Religious Organizations, Commercial TV & Radio Stations, Education Colleges & Universities, Education K-12, Education Online, Education Trades, Entertainment Industry, Finance, Foreign & Defense Policy, Government - International, Government - National, Government - State and Local, Government Regulators, Hospitality, Human Resources, Information Technology, Lawyers/Law Firms/Legal Industry, Magazines, National Security, News Media, Non-profits/Foundations/Philanthropists, Online Media, Professional Services, Radio/TV Stations, Technology Company, TV Production, TV/Movies/Music, Work (Future of)