Compressed low-resolution image restoration method based on combined deep network

Abstract

The present invention provides a compressed low-resolution image restoration method based on a combined deep network, belonging to the digital image / video signal processing field. The compressed low-resolution image restoration method based on the combined deep network starts from the aspect of the coprocessing of the compression artifact and downsampling factors to complete the restoration of a degraded image with the random combination of the compression artifact and the low resolution; the network provided by the invention comprises 28 convolution layers to establish a leptosomatic network structure, according to the idea of transfer learning, a model trained in advance employs a fine tuning mode to complete the training convergence of a greatly deep network so as to solve the problems of vanishing gradients and gradient explosion; the compressed low-resolution image restoration method completes the setting of the network model parameters through feature visualization, and the relation of the end-to-end learning degeneration feature and the ideal features omits the preprocessing and postprocessing; and finally, three important fusions are completed, namely the fusion of the feature figures with the same size, the fusion of residual images and the fusion of the high-frequency information and the high-frequency initial estimation figure, and the compressed low-resolution image restoration method can solve the super-resolution restoration problem of the low-resolution image with the compression artifact.

Description

technical field [0001] The invention belongs to the field of digital image / video signal processing, in particular to a method for restoring compressed low-resolution images based on a joint deep network. Background technique [0002] With the rapid development and wide application of multimedia technology, high-quality images and videos have become a mainstream demand. The higher the quality of video data, the greater its analysis value. However, affected by factors such as limited channel bandwidth and storage capacity, images and videos have been compressed for transmission and normal storage. The most common image degradation factors are downsampling and compression artifacts. Downsampling reduces the spatial resolution of an image, and compression artifacts lead to image blockiness, ringing, and blurring. Therefore, it is of great theoretical significance and practical application value to study image restoration technology with multiple degradation factors for low-re...

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to overcome the deficiencies of the prior art, and to provide a joint deep network for decompression distortion and super-resolution restoration for low-quality images that contain both compression distortion and low-resolution degradation problems, so that it can cooperate Solving the problem of super-resolution restoration of low-resolution images with compression artifacts

Images