ALEXANDRIA, Va., July 9 -- United States Patent no. 12,354,241, issued on July 8, was assigned to Hong Kong Applied Science and Technology Research Institute Co. Ltd. (Hong Kong, Hong Kong).
"Diffusion-based multiple-modality image fusion" was invented by Zhihan Wang (Hong Kong, Hong Kong) and Yan Huo (Shenzhen, China).
According to the abstract* released by the U.S. Patent & Trademark Office: "An image-guided diffusion network has two Convolution Neural Networks (CNNs). A RGB image and an IR image are concatenated with a Gaussian noise image and input to a denoising neural network that merges information from the RGB and IR images as noise is removed over many iterations. Then an enhancement neural network up-samples for Super Resolution...