Real image denoising method based on pseudo 3D autocorrelation network

Abstract

The invention discloses a real image denoising method based on a pseudo 3D self-correlation network, and the method comprises the steps: constructing a pseudo 3D self-correlation module P3AB based on one-dimensional fast convolution so as to extract the self-correlation features of elements at each position of an input feature map in horizontal, vertical and channel directions through the one-dimensional fast convolution, and after the traversal of all positions is completed, respectively obtaining pseudo 3D self-correlation features in three directions; performing channel cascading and adaptive feature fusion on the pseudo 3D self-correlation features in the three directions to obtain global self-correlation features including spatial domain self-correlation information and channel domain self-correlation information; adding the global self-correlation feature and the input feature map through residual connection to serve as the output of the P3AB; constructing a pseudo 3D autocorrelation network P3AN, the P3AN comprises a shallow feature extraction unit, a stacked P3AB and a tail convolutional layer, and is provided with two layers of jump connection; training the P3AN; and de-noising an input real noise image by using the trained P3AN, and outputting a de-noised image.

Description

technical field [0001] The invention relates to the fields of computer vision and image processing, in particular to a real image denoising method based on a pseudo 3D autocorrelation network. Background technique [0002] The noise in natural images often has multiple sources, such as dark current noise in the capture instrument and random disturbance in the transmission medium. At present, a large number of advanced methods have achieved remarkable results in removing synthetic Gaussian white noise. However, noise in real images often has complex generation processes in CCD or CMOS camera systems, and they are usually non-Gaussian and non-uniform. Therefore, in the restoration task of real noisy images, it is difficult for denoising algorithms based on synthetic data to accurately simulate and remove irregular noise. For blind image denoising, due to the lack of a specific noise prior, the input low-quality noisy image becomes the only source of information. Therefore, ...

AI Technical Summary

Problems solved by technology

[0006] The main purpose of the present invention is to propose a real image denoising method based on a pseudo 3D autocorrelation network, which solves the problems of poor denoising effect, high complexity of denoising model and large computational burden in current denoising methods of real noisy images. question

Images