Super-resolution method and device, terminal equipment and storage medium

Abstract

The invention provides a super-resolution method and device, terminal equipment and a storage medium, relates to the technical field of deep learning, and can reduce the calculation amount. The super-resolution method comprises the following steps: inputting a to-be-processed low-resolution image into a trained classification super-resolution network model for processing, and outputting to obtain a high-resolution image corresponding to the low-resolution image, wherein the classification and super-resolution network model comprises a classification model and a plurality of super-resolution network models with different complexities, and the processing process of the classification and super-resolution network model on the low-resolution image comprises the following steps of: cutting the low-resolution image into a plurality of sub-images; for each subimage, determining the complexity of the subimage according to the classification model, inputting the subimage into a super-resolution network model corresponding to the complexity of the subimage in the plurality of super-resolution network models for processing, and outputting a reconstructed image of the obtained subimage; and splicing the reconstructed images of the sub-images to obtain a high-resolution image.

Description

technical field [0001] The present application relates to the field of deep learning technology, and in particular to a super-resolution method, device, terminal equipment and storage medium. Background technique [0002] Super-resolution technology refers to the technology of reconstructing low-resolution images into high-resolution images. The super-resolution algorithm based on deep learning is currently the most commonly used super-resolution method. The super-resolution algorithm based on deep learning is to cut the low-resolution image into sub-images, and then input each sub-image into the super-resolution network model for processing to obtain the reconstructed image, and stitch the reconstructed images of each sub-image Get high resolution images. [0003] At present, the more commonly used super-resolution network models include Accelerating the Super-Resolution Convolutional Neural Network (FSRCNN), fast, accurate, lightweight super-resolution and cascaded resid...

AI Technical Summary

Problems solved by technology

These super-resolution network models have a large amount of calculation in the process of super-resolution processing of low-resolution images, resulting in slow processing speed.

Images