ALEXANDRIA, Va., July 16 -- United States Patent no. 12,670,659, issued on June 30, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Generative modeling of three dimensional scenes and applications to inverse problems" was invented by Wen-Sheng Chu (Santa Clara, Calif.), Dmitry Lagun (San Jose, Calif.), Ioannis Daras (Austin, Texas) and Abhishek Kumar (Milpitas, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods for training a generative neural radiance field model can include geometric regularization. Geometric regularization can involve the utilization of reference geometry data and/or an output of a surface prediction model. The geometry regularization can train the generative n...