Image reconstruction model training method, image reconstruction method, equipment and medium

Abstract

The invention discloses an image reconstruction model training method, an image reconstruction method, equipment and a medium. The method comprises the following steps: acquiring an original high-resolution image and an original low-resolution image; inputting the original low-resolution image into a first generation network for image super-resolution reconstruction to obtain a pseudo high-resolution image; inputting the original high-resolution image and the pseudo high-resolution image into a first discrimination network for discrimination, and obtaining a first discrimination result; inputting the original high-resolution image and the pseudo high-resolution image into a perception loss network to obtain a perception loss value; and based on the perception loss value and the first discrimination result, updating model parameters of the first generation network and the first discrimination network, and obtaining a target generation network based on super-resolution reconstruction. The target generation network can reconstruct images with high resolution and containing texture features and structural features of different scales, and has high perception quality.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image reconstruction model training method, image reconstruction method, equipment and media. Background technique [0002] In the field of image processing technology, image resolution is one of the main technical indicators that characterize the image observation level. Image resolution usually refers to the spatial resolution of the image. The higher the image resolution, the finer the details of the scene that the image can reflect, and the more information it can provide. Due to the limitation of objective conditions, high-quality images are often not obtained in real application environments. Therefore, it is very important to study advanced image super-resolution reconstruction technology to improve image recognition ability and recognition accuracy. [0003] Image super-resolution reconstruction technology refers to the technology of converting lower...

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide an image reconstruction model training method, image reconstruction method, equipment, and media to solve the problem of low perceived quality of images generated during the current image super-resolution reconstruction process

Images