ALEXANDRIA, Va., Oct. 27 -- United States Patent no. 12,776,074, issued on Oct. 27, was assigned to NVIDIA Corp. (Santa Clara, Calif.).
"Table dictionaries for compressing neural graphics primitives" was invented by Alexander Georg Keller (Berlin), Thomas Muller-Hohne (Rheinfelden, Germany) and Towaki Takikawa (Toronto).
According to the abstract* released by the U.S. Patent & Trademark Office: "Neural network performance is improved in terms of training speed, memory footprint, and/or accuracy by learning a compressed neural graphics primitive representation. A neural graphics primitive is a mathematical function involving at least one neural network, used to represent a computer graphic, where the graphic can be an image, a 3D shape, a ...