Image denoising method based on adaptive consistency priori deep network

• Main Authors: HE XIAOHAI, XIONG SHUHUA, REN CHAO, WU XIAOHONG, TENG QIZHI, PAN YIZHONG
• Format: Patent
• Language: Chinese; English
• Published: 19.07.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses an image denoising method based on an adaptive consistency priori deep network. The method mainly comprises the following steps: constructing adaptive consistency priori on the basis of consistency priori; constructing an image denoising cost function solved in the feature domain according to the adaptive consistency priori obtained in the previous step; optimizing the cost function constructed in the previous step by using a gradient-based method to obtain an image denoising iteration framework based on the adaptive consistency priori deep network; expanding the iteration framework into a deep neural network model; training the constructed deep neural network model; and taking a noise image as input, and obtaining a recovered high-quality image by using the deep neural network model trained in the previous step. According to the method, a good denoising effect can be obtained, and the method is an effective image denoising method. 本发明公开了一种基于自适应一致性先验深度网络的图像去噪方法。主要包括以下步骤：在一致性先验的基础上构建了自适