Nvidia has announced a breakthrough in 3D rendering research that may have far-reaching ramifications for future virtual worlds. A team led by Nvidia VP Bryan Catanzaro discovered a way to use a neural network to render synthetic 3D environments in real time, using a model trained on real-world videos. With Nvidia's technology, worlds can be populated with objects "learned" from video input. Nvidia's technology offers the potential to quickly create virtual worlds for gaming, automotive, architecture, robotics or virtual reality.