Machine-learning system generates real-time scenes in 3D from images; about 15,000 times faster than other methods

https://news.mit.edu/2021/3-d-image-rendering-1207

"To represent a 3D scene from a 2D image, a light field networ (LFN) encodes the 360-degree light field of the 3D scene into a neural network that directly maps each camera ray to the color observed by that ray... can reconstruct a light field after only a single observation of an image, and they are able to render 3D scenes at real-time frame rates...The LFN can tell the depth of objects in a scene due to parallax, and uses this information to encode a scene’s geometry as well as its appearance"