US Patent Issued to Intel on April 14 for "Video codec assisted real-time video enhancement using deep learning" (American, Chinese Inventors)

ALEXANDRIA, Va., April 15 -- United States Patent no. 12,604,021, issued on April 14, was assigned to Intel Corp. (Santa Clara, Calif.).

"Video codec assisted real-time video enhancement using deep learning" was invented by Chen Wang (San Jose, Calif.), Ximin Zhang (San Jose, Calif.), Huan Dou (Beijing), Yi-Jen Chiu (San Jose, Calif.) and Sang-Hee Lee (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques related to accelerated video enhancement using deep learning selectively applied based on video codec information are discussed. Such techniques include applying a deep learning video enhancement network selectively to decoded non-skip blocks that are in low quantization parameter frame...