Image reconstruction model training method and image super-resolution reconstruction method and device

Abstract

The invention discloses an image reconstruction model training method and an image super-resolution reconstruction method and device, and belongs to the technical field of image super-resolution. Themethod comprises the steps of obtaining a sample set by preprocessing an image, establishing an image reconstruction model for image super-resolution reconstruction; using the sample set to train andtest the image reconstruction model; in the image reconstruction model, using a feature extraction network for performing feature extraction on a low-resolution image and inputting into a first residual network, wherein the m cascaded residual networks are respectively used for carrying out feature extraction on an output image of a previous network and then superposing the output image with the image, m attention networks are respectively used for extracting images of a region of interest from the output images of the m residual network, and an amplification network is used for fusing and amplifying the output images of the attention networks and the m residual networks, so that the output images and the image subjected to bicubic interpolation amplification are fused by the first fusionlayer. According to the present invention, the visual effect of the reconstructed image can be effectively improved.

Description

technical field [0001] The invention belongs to the technical field of image super-resolution, and more specifically relates to an image reconstruction model training method, an image super-resolution reconstruction method and a device. Background technique [0002] Image resolution generally refers to the ability of an imaging or display system to distinguish details, and represents the amount of information stored in an image, usually expressed as "number of horizontal pixels × number of vertical pixels". Generally, the higher the resolution of the image, the more details the image contains and the greater the amount of information provided. Image super-resolution technology (Image Super-Resolution, referred to as SR) is a technology for reconstructing high-resolution (High Resolution, referred to as HR) images based on a single or multiple low-resolution (Low Resolution, referred to as LR) images. Being able to provide richer visual information is a classic problem in th...

AI Technical Summary

Problems solved by technology

However, the visual effects of images reconstructed by these methods need to be improved, and in order to obtain clearer images, the model training time is often longer

Images