Image processing method and related equipment

Abstract

The invention relates to the field of artificial intelligence, and discloses an image processing method, which comprises the following steps: acquiring a first image; carrying out feature extraction on the first image to obtain at least one first feature map, wherein the at least one first feature map comprises N first feature values, and N is a positive integer; acquiring a target compression code rate, which corresponds to M target gain values, wherein each target gain value corresponds to one first feature value, and M is a positive integer smaller than or equal to N; processing the corresponding first feature values according to the M target gain values to obtain M second feature values; and performing quantization and entropy coding on the processed at least one first feature map to obtain coded data, the processed at least one first feature map comprising the M second feature values. Compression code rate control can be realized in the same compression model.

Description

technical field [0001] This application relates to the field of artificial intelligence, in particular to an image processing method and related equipment. Background technique [0002] Today multimedia data accounts for the vast majority of Internet traffic. The 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 various international standards, such as JPEG, JPEG2000, WebP, BPG and other image coding standards. Although these encoding methods have been widely used at present, these traditional methods have shown some limitations for the increasing amount of image data and emerging new media types. [0004] In recent years, researchers have begun to carry out research on image coding methods based on deep learning. Some researchers ha...

AI Technical Summary

Problems solved by technology

However, most of the current image encoding based on deep convolutional networks has a defect, that is, a trained model can only output one encoding result for an input image, and cannot obtain the encoding effect of the target compression rate according to actual needs.

Images