Image processing method and related equipment

Abstract

The invention relates to the field of artificial intelligence, and discloses an image processing method, and the method comprises the steps: obtaining first coded data which is obtained through the coding of a first image; performing entropy decoding on the first coded data to obtain at least one first feature map; the at least one first feature map is processed through a generative model to obtain at least one second feature map, and image high-frequency information included in the at least one second feature map is more than image high-frequency information included in the at least one first feature map; and performing image reconstruction on the at least one second feature map to obtain a second image. The image high-frequency information included in the at least one second feature map obtained through the generation model is more than the image high-frequency information included in the at least one first feature map, so that the texture details included in the reconstructed second image are more than the texture details of the image obtained by performing image reconstruction on the at least one first feature map; and the subjective feeling of the reconstructed image is improved.

Description

technical field [0001] The present application relates to the field of artificial intelligence, and in particular, to an image processing method and related equipment. Background technique [0002] Multimedia data now accounts for the vast majority of Internet traffic. Compression of image data plays a vital role in the storage and efficient transmission of multimedia data. So image coding is a technology with great practical value. [0003] The research on image coding has a long history. Researchers have proposed a large number of methods and formulated a variety of international standards, such as JPEG, JPEG2000, WebP, BPG and other image coding standards. Although these coding methods have been widely used at present, these traditional methods show some limitations in view of the increasing amount of image data and the emerging new media types. [0004] In recent years, researchers have begun to carry out research on image coding methods based on deep learning. Some ...

AI Technical Summary

Problems solved by technology

However, the model obtained by end-to-end optimization using PSNR or MS-SSIM as the image distortion degree surpasses the traditional image compression algorithm in this index, but the subjective feeling of the reconstructed image is poor

Images