Title：Image blind denoising system
Country：China
Patent No.：201911307908.6
Legal Status：Under review
Inventor：Xiang Xie, Shaofeng Zou, Guolin Li, Zhihua Wang
Assignee：International Graduate School at Shenzhen, Tsinghua University; Tsinghua University
Address：Tsinghua Campus, Xili University Town, Nanshan District, Shenzhen City 518055, Guangdong Province
Filing Date：2019-12-18
Issue Date：
Abstract：
The invention relates to an image blind denoising system which comprises: a blind denoising network module used for removing noise of an input image, wherein the blind denoising network module directly reconstructs a noisy image by using a pre-training model so as to reduce the number of iterations required for generating an optimal reconstructed image. An encoder-decoder structure with jump connection is adopted, only white Gaussian noise is used as network input, a noisy image is used as a reference image, and a mean square error is used as a loss function; and the blind image quality evaluation network module is used for evaluating the noise image reconstructed by the blind denoising network module, deciding when to terminate the iterative process of the blind denoising network module,and selecting the reconstructed image with the highest score as a final denoised image.
Patent Certificate：
PDF/Jpg