首页|'Super-Resolution On Text-To-Image Synthesis With Gans' in Patent Application Ap proval Process (USPTO 20240281924)
'Super-Resolution On Text-To-Image Synthesis With Gans' in Patent Application Ap proval Process (USPTO 20240281924)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
The following quote was obtained by the news editors from the background informa tion supplied bythe inventors: “The following relates to digital image processi ng using machine learning. Digital imageprocessing refers to the use of a compu ter to edit a digital image using an algorithm or a processingnetwork. In some cases, image processing software can be used for various tasks, such as image ed iting,enhancement, restoration, image generation, etc. Some image generation sy stems implement machinelearning techniques to generate a set of images based on a text prompt where the set of images vary intexture and details. In some exam ples, image generation (a subfield of image processing) includes the useof a st yle-based model to generate images based on an input condition (e.g., text promp t). Commonstyle-based models include generative adversarial network (GAN), Styl eGAN, StyleGAN2, CoModGAN. AStyleGAN model includes a mapping network and a syn thesis network.”
NETL
NSTL
