ALEXANDRIA, Va., April 15 -- United States Patent no. 12,602,942, issued on April 14, was assigned to Snap Inc. (Santa Monica, Calif.).

"Model fine-tuning for automated augmented reality descriptions" was invented by Maksim Gusarov (Santa Monica, Calif.), Kwot Sin Lee (Weehawken, N.J.), Patrick Poirson (Gilbert, Ariz.) and Chen Wang (Great Neck, N.Y.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A second input image is generated by applying a target augmented reality (AR) effect to a first input image. The first input image and the second input image are provided to a first visual-semantic machine learning model to obtain output describing at least one feature of the target AR effect. The first visual-seman...