Model training method and device, image super-resolution processing method and device, terminal and storage medium

Abstract

The invention provides a model training method and device, an image super-resolution processing method and device, a terminal and a storage medium, and relates to the technical field of model training. The method comprises the following steps: carrying out downsampling on an original high-resolution image corresponding to a sample low-resolution image to obtain a high-resolution image comprising multiple resolutions of the original high resolution; respectively adopting a plurality of feature extraction branches to carry out feature extraction on the sample low-resolution image to obtain imagefeatures of a plurality of levels; a feature fusion module is adopted to perform fusion processing on the image features of the multiple levels to obtain fusion features of the sample low-resolutionimage; reconstructing the fused features by adopting a plurality of reconstruction branches to obtain super-resolution images with a plurality of resolutions; and training the neural network model according to the high-resolution images with the plurality of resolutions and the corresponding super-resolution images. The low-resolution image is recovered through the neural network model, semantic information contained in the generated super-resolution image is richer, and the definition is higher.

Description

technical field [0001] The present invention relates to the technical field of model training, in particular to a method, device, terminal and storage medium for model training and image super-resolution processing. Background technique [0002] Image resolution refers to the amount of information stored in the image, which is how many pixels per inch of the image. Low-resolution images are less clear and contain fewer features. Restoring a low image resolution image to a super-resolution image can improve the clarity of the image and make the details contained in the image more realistic. [0003] In related technologies, by setting multiple feature extraction blocks, multiple scale feature extraction blocks are sequentially connected in series, so as to extract image features of different levels through the series of multiple feature extraction blocks, and generate super-resolution images according to image features of different levels. [0004] However, in related techn...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a model training, image super-resolution processing method, device, terminal and storage medium to solve the problem of image extraction through multiple feature extraction blocks connected in series in the related art. Features, directly generate super-resolution images, there will be more noise and artifacts in the generated super-resolution images, resulting in poor clarity of the generated super-resolution images

Images