ALEXANDRIA, Va., Nov. 3 -- United States Patent no. 12,784,339, issued on Nov. 3, was assigned to Nvidia Corp. (Santa Clara, Calif.).
"Unsupervised learning of scene structure for synthetic data generation" was invented by Jeevan Devaranjan (Toronto), Sanja Fidler (Toronto) and Amlan Kar (Toronto).
According to the abstract* released by the U.S. Patent & Trademark Office: "A rule set or scene grammar can be used to generate a scene graph that represents the structure and visual parameters of objects in a scene. A renderer can take this scene graph as input and, with a library of content for assets identified in the scene graph, can generate a synthetic image of a scene that has the desired scene structure without the need for manual place...