US Patent Issued to Amazon Technologies on March 17 for "Machine-learning models for generating a refined image" (Pennsylvania, California, Washington Inventors)

ALEXANDRIA, Va., March 17 -- United States Patent no. 12,579,615, issued on March 17, was assigned to Amazon Technologies Inc. (Seattle).

"Machine-learning models for generating a refined image" was invented by Cong Chen (Pittsburgh), Maxim Arap (San Jose, Calif.), Cong Phuoc Huynh (Palo Alto, Calif.), Sheng Liu (Bellevue, Wash.), Muhammad Raffay Hamid (Seattle) and Mohammad Haroon Abuomar (Redmond, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method can be used to generate a composite image. Image data can be received, and a low-resolution composite image can be generated. A first machine-learning model can be applied to the low-resolution image and to a mask of the image data...