Intellindust Information Technology (Shenzhen) Co., Ltd.

Peizhe Ru

Lin Wang

Xiao Zhou

Caizhi Zhu

Yaohui Sun

The embodiments of the present application provide a denoising method, apparatus, electronic device and medium, which relates to the technical field of image processing. The method comprises: inputting an image to be processed into an image denoising model, which is a model obtained by training a convolutional neural network model based on a preset training set, wherein the preset training set includes multiple groups of annotation data and sample data corresponding to each group of annotation data, and each group of annotation data includes multiple noiseless images obtained by performing motion simulation processing on one reference noiseless image, and the sample data corresponding to the group of annotation data includes images obtained by superimposing noise to the multiple noiseless images respectively; acquiring denoised image data output by the image denoising model; converting the image data into an image, to obtain a denoised image corresponding to the image to be processed. This can effectively solve the problem of ghost existed in the denoised image.

Denoising method, apparatus, electronic device and medium

A method and an apparatus for generating image data, which relate to the technical field of image processing. The method comprises: obtaining a first pixel value of each pixel in a first image based on original pixel values of the first image acquired by an image acquisition device when ambient light brightness is greater than a first preset brightness threshold; obtaining a second pixel value of each pixel by dividing the first pixel value of this pixel by a preset multiple; the second preset brightness threshold is less than the first preset brightness threshold; obtaining a third pixel value of each pixel by adding Poisson noise based on a total system gain of the image acquisition device on the basis of the second pixel value of this pixel; generating original pixel values of a target image which corresponds to the first image for which the ambient light brightness is less than the second preset brightness threshold based on respective third pixel values. In this way, the generation efficiency of image data can be improved.

Growing community of inventors

Shenzhen, China

Peizhe Ru