Blind Image Restoration Based on Local Maximum Gradient Prior and ADMM
YU Lun
WANG Yijun
XING Xiaoxiao
Abstract：In order to estimate fuzzy kernel more accurately and improve the quality of moving image deblurring,a blind resto-ration algorithm based on local maximum gradient prior and ADMM is proposed.Firstly,a point spread function estimation model that integrates the local maximum gradient prior and the maximum a posteriori probability is proposed.The non-convex optimization problem of the model is iteratively solved through the semi-quadratic splitting algorithm.Then the fuzzy kernel is estimated by multi-scale iteration to make the fuzzy kernel obtained by the final iteration more accurate.Finally,the robust ADMM is used to achieve fast image deblurring.Experiments show that the proposed algorithm has more image details than the contrast algorithm,and can effectively suppress ringing and artifact phenomena.
Keywords：blind image restorationlocal maximum gradient priorADMMhalf quadratic splitfuzzy kernel
Publication Date：2025-06-20
Online Publishing Date：2025-09-23(First online date of this platform, not the publication date of the document)
Pages：5( 36-39,50 )