Abstract
Reporters obtained the following quote from the background information supplied by the inventors:“The following relates generally to machine learning, and more specifically to machine learning for imageediting. Digital image processing ge nerally refers to the process of making changes to a digital image usinga compu ter or other electronic device. A computer or other electronic device may use an algorithm, aprocessing network, etc. to make changes to a digital image. In so me cases, image processing software maybe used for various image processing tas ks, such as image editing, image generation, etc. Some imageprocessing systems may implement machine learning techniques, for example, to perform tasks using predictive models (e.g., without explicitly programing the system for each task), to perform tasks with moreaccuracy or in less time, to perform tasks using spe cial-purpose hardware, etc. Examples of machinelearning architectures used for generating image data include generative adversarial networks (GANs) anddiffusi on models.”
NETL
NSTL