Image processing method, training method and device of image processing model, and medium

Abstract

The invention relates to an image processing method, a training method and device of an image processing model, and a medium. The image processing method comprises the steps of determining sensitivity information of a to-be-processed image; determining a target sensitivity feature map corresponding to the to-be-processed image according to the sensitivity information of the to-be-processed image; inputting the to-be-processed image and the target sensitivity feature map into an image processing model to obtain a target image output by the image processing model, the image processing model being obtained by training an initial image processing model through a training set, the training set comprising a plurality of groups of training samples, and the target sensitivity feature map comprising a plurality of groups of target sensitivity feature maps, and each group of training samples comprising a first image containing noise information, a light sensitivity characteristic pattern corresponding to the first image, and a second image which corresponds to the first image and does not contain noise information. Therefore, the fineness and the accuracy of image processing can be improved, and the quality of the determined target image is improved.

Description

technical field [0001] The present disclosure relates to the field of image processing, and in particular, to an image processing method, a training method, a device, and a medium for an image processing model. Background technique [0002] With the development of computer technology and cameras, users have higher and higher requirements for the quality of pictures taken. In the related art, if the quality of the captured picture is low, it can be denoised based on the deep learning model, so as to obtain a picture with better quality. However, in the above process, the image is usually directly input into the model for processing, and the accuracy of image processing is low, so it is difficult to denoise according to the user's needs. Contents of the invention [0003] In order to overcome the problems existing in related technologies, the present disclosure provides a high-precision image processing method, a training method, device, and medium for an image processing m...

AI Technical Summary

Problems solved by technology

However, in the above process, the image is usually directly input into the model for processing, the accuracy of image processing is low, and it is difficult to denoise according to the user's needs.

Images