Image de-noising method and device, electronic equipment and image super-division de-noising method

Abstract

The invention discloses an image denoising method and device, electronic equipment and an image super-division denoising method. The image denoising method comprises the following steps: respectivelyacquiring a first noiseless image and a second noiseless image with different image contents; performing alternate iterative training on the initial noise generation network and the discrimination network by using the first image and the second image to obtain a newly-built noise generation network; inputting the first image into a newly-built noise generation network, and outputting a third imagewith analog noise; training the initial image denoising network by using the first image and the third image as paired training samples to obtain a trained newly-built image denoising network, wherein the newly-built image denoising network is configured to convert the original image with noise into a noiseless newly-built image. According to the image denoising method, the image denoising network used for converting the low-resolution image into the high-resolution image can be obtained by training the asymmetric training set, and the image super-resolution effect is improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image denoising method, device, electronic equipment, and image super-resolution denoising method. Background technique [0002] Image super-resolution refers to recovering a high-resolution image from a low-resolution image or image sequence. High-resolution images have high pixel density, which can provide more details, which often play a key role in practical applications. To obtain high-resolution images, the most direct method is to use a high-resolution image sensor, but due to the limitations of the manufacturing process and cost of sensors and optical devices, this method is difficult to achieve in many occasions and large-scale deployment. Therefore, it is of great practical significance to obtain high-resolution images through super-resolution algorithms using existing equipment. [0003] At present, most super-resolution algorithms are trained bas...

AI Technical Summary

Problems solved by technology

[0003] At present, most super-resolution algorithms are trained based on paired data sets to obtain models. When the model is applied to low-resolution images that are different from the distribution of training data sets, the effect of image super-resolution is not good, and it is easy to appear. Various artifacts

Images