US Patent Issued to QUALCOMM on Sept. 15 for "Text-to-image diffusion models for generalizable mesh generation" (Canadian, Greek, American Inventors)

ALEXANDRIA, Va., Sept. 15 -- United States Patent no. 12,737,981, issued on Sept. 15, was assigned to QUALCOMM Inc. (San Diego).

"Text-to-image diffusion models for generalizable mesh generation" was invented by Antoine Clement Mercier (Loutraki, Greece), Guillaume Jean Fernand Berger (Toronto), Fatih Murat Porikli (San Diego) and Ramin Ebrahim Nakhli (Thornhill, Canada).

According to the abstract* released by the U.S. Patent & Trademark Office: "Certain aspects of the present disclosure provide techniques and apparatus for improved machine learning. In an example method, a multiview latent tensor is generated based on processing a textual input using a diffusion machine learning model, where the multiview latent tensor corresponds to a p...