A variable magnification image super-resolution network model

Abstract

The invention discloses a variable magnification image super-resolution network model, the model includes a parameterized residual learning network PRNet, a residual refined learning network RRNet and a superposition network; a parameterized residual learning network PRNet is used for learning low Mapping between resolution LR images and high-resolution HR images; Residual Refinement Learning Network RRNet, used to learn to reconstruct the mapping between high-resolution images and residual images; Overlay network, used to combine high-resolution HR images with The residual images are superimposed to form the final super-resolution SR image output. The present invention establishes a parameterized residual learning network model by explicitly expressing the magnification parameter, so that the model can accept input of any scale and meet the task requirements of variable magnification super-resolution; the present invention proposes a residual refined learning network , and further learn the mapping relationship between the reconstructed high-resolution image and the reconstruction residual, so as to compensate the residual of the reconstructed image and improve the quality of super-resolution reconstruction.

Description

technical field [0001] The invention belongs to the technical field of digital image processing and relates to an image super-resolution network model, in particular to an image super-resolution network model with variable magnification. [0002] technical background [0003] Deep learning technology has promoted a huge leap in image super-resolution (SR) reconstruction performance, but the deep learning model for super-resolution reconstruction can only target a fixed magnification at a time. If different magnifications are to be performed simultaneously For super-resolution tasks, it is necessary to train multiple deep learning network models corresponding to different magnifications. This limitation of super-resolution networks restricts their practical applications for applications that need to perform arbitrary indeterminate magnifications. [0004] Super-resolution application scenarios with uncertain magnification are ubiquitous in reality. A common scenario is face s...

AI Technical Summary

Problems solved by technology

[0006] It can be seen that for the super-resolution task of variable magnification, the current two processing methods have serious defects, and the way of training the corresponding network model for each multiple is cumbersome and impractical; first interpolate to a uniform resolution and then super-resolution reconstruction The method ignores the differences in content components of input images with different resolutions, and it is difficult to obtain ideal reconstruction effects.

The reason why a network trained for one magnification (such as X2) cannot be applied to another magnification (such as X3) is that the existing super-resolution reconstruction network does not explicitly express the variable of magnification. Therefore, it is necessary to propose a super-resolution network model with variable magnification to meet the requirements of arbitrary scale input

Images