Image restoration method based on adaptive residual neural network

Abstract

The invention discloses an image restoration method based on an adaptive residual neural network. The method comprises the steps that an adaptive residual neural network model is built, wherein the adaptive residual neural network comprises a number of adaptive residual units connected in series; training sets for image denoising, image super-resolution and image deblocking effects are respectively selected, and corresponding training parameters are respectively set; according to the adaptive residual neural network model and the training parameters for image denoising, image super-resolution and image deblocking effects, the corresponding target neural network model is trained respectively with the goal of minimizing a loss function; and according to the trained target neural network model for the problem of image denoising, image super-resolution and image deblocking effects, an image to be processed is input to the corresponding target neural network model, and a corresponding high-quality image is output. According to the invention, the PSNR, SSIM and visual effect of the image can be remarkably improved, and the method has the advantages of good recovery effect, high speed and strong robustness.

Description

technical field [0001] The invention relates to the fields of computer vision and digital image processing, in particular to an image restoration method based on an adaptive residual neural network. Background technique [0002] Image restoration is a classic and fundamental problem in computer vision and image processing. It is a necessary preprocessing process to solve many related problems. Its purpose is to recover a potential high-quality image X from a low-quality image Y. The process can be expressed as: Y=AX+N, where N is usually considered as additive white Gaussian noise (Additive White Gassian, AWG), which is a typical ill-conditioned linear inverse problem. If the only source of image damage is Gaussian white noise, the problem becomes image denoising; if there is no noise, and A is a downsampling factor, the problem becomes image superresolution; if there is no noise, and A is a JPEG compression quality parameter, the problem becomes image deblocking. The meth...

AI Technical Summary

Problems solved by technology

In addition, ARCNN was the first to apply the neural network method to remove the block effect. This method is similar to SRCNN. It builds a 4-layer convolutional neural network for mapping learning, and predicts high-quality images through the trained model. Therefore, the shortcomings of this method Also similar to ARCNN

[0006] The current methods are basically only able to solve one of the three problems of the image, and there is a lack of a method that can solve these three restoration problems of the image at the same time.

Images