Image denoising method based on pixel-level global noise estimation coding and decoding network

Abstract

The invention relates to an image denoising method based on a pixel-level global noise estimation coding and decoding network, and the method comprises the steps: inputting an original noisy image into an input module of the coding network, carrying out the preliminary feature extraction of the original noisy image through convolution, and outputting an original feature map; processing the original feature map through a plurality of cascaded coding modules in the coding network, and outputting a denoised high-level feature map with a relatively small spatial size and a relatively high semanticlevel; processing the high-level feature map through a plurality of decoding modules with skip connection structures in a decoding network symmetrical to the encoding network, and obtaining an outputfeature map after noise removal considering space information and semantic information; and mapping the output feature map of the decoding network to an output feature dimension by using convolutionprocessing through an output module of the decoding network, and outputting a final clear image. According to the method, real image noise, global information and pixel value related characteristics are fully considered, and the denoising effect and the operation speed are both considered.

Description

technical field [0001] The invention relates to the technical field of computer vision images, in particular to an image denoising method based on a pixel-level global noise estimation codec network. Background technique [0002] As an important information carrier, digital images are playing an increasingly important role in daily production and life. Image information is widely used in aerospace, industrial production, military, medical, communication, etc. because of its intuitive and vivid features and large amount of information. Fields are closely related to our work and life. However, digital images in reality are often affected by the interference of imaging equipment and external environmental noise during the digitization and transmission process, which leads to the degradation of image quality and brings difficulties for subsequent research and processing. Therefore, image denoising, as a basic and very important low-level computer vision task, has high scientifi...

AI Technical Summary

Problems solved by technology

However, the above-mentioned deep learning method is aimed at artificially adding Gaussian noise to the synthetic image. The Gaussian noise in the image has nothing to do with the pixel value. It fails to take into account that the noise of the real-world image is not only Gaussian, but also related to the pixel value itself. Correlation, so the above method has poor generalization ability on real noisy images, thus achieving more limited effect

Images