Light-weight image super-resolution reconstruction method based on progressive distillation network

Abstract

The invention relates to a lightweight image super-resolution reconstruction method based on a progressive distillation network, and relates to the technical field of image super-resolution reconstruction, and the method comprises the steps: carrying out the improvement of an existing super-resolution convolutional neural network model, including the steps: according to the receptive field progressive principle of convolution kernels with different expansion rates, utilizing two different progressive distillation connection combinations to replace original feature distillation connection, and adopting an asymmetric expansion convolution residual block, so the network can fully extract edge and texture feature information of an image under the condition of extremely few parameters; utilizing a channel shuffling structure to improve hierarchical features of distillation network connection, and further improving feature sharing among channels, so the accuracy of image super-resolution reconstruction is improved; further adopting a multi-scale space attention mechanism module, so the weight of the fusion features can be recalibrated in a self-adaptive mode; wherein the post-up-sampling reconstruction part is an up-sampling-based three-dimensional pixel attention mechanism method, and the efficiency of super-resolution image reconstruction is further improved.

Description

technical field [0001] The present disclosure relates to the technical field of image super-resolution reconstruction, in particular to a lightweight image super-resolution reconstruction method based on a progressive distillation network. Background technique [0002] With the popularization and rapid development of various image display devices, mobile devices and network construction, the requirements for image and video quality continue to increase. How to obtain better and more economical high-resolution images or videos has become more and more important. more important. However, in practice, the acquisition and processing of digital images will be affected by many factors, resulting in lower image quality, and ideal images are often not obtained on image display devices. Therefore, how to obtain cost-effective and high-quality images has become an urgent problem to be solved. [0003] Single image super-resolution is a technique to reconstruct a high-resolution imag...

AI Technical Summary

Problems solved by technology

[0003] Single image super-resolution is a technique of reconstructing a high-resolution image from a low-resolution image through an identity mapping function, but this is a pathological problem, because one low-resolution image can reconstruct multiple high-resolution images

Images