Image Deblurring Based On Multi-Direction Weighted TV And Adaptive Weighted TGV

Image deblurring algorithms have been the focus and difficulty in the field of image processing and computer vision,the most studied and widely used is the total variation regularization model and related algorithms.In this paper,the traditional total variation regularization deblurring model is studied,which has the advantages of limited detail restoration ability,sensitive to noise,and only using the staircase feature of image,an image deblurring model based on multi direction weighted TV and adaptive weighted TGV is proposed,and the optimal numerical algorithm for the new model is also given.The details are as follows:In the field of image blind deblurring,in order to overcome the limitations of traditional TV regularization in image restoration with the deficient ability of detail recovery and sensitivity to the noise,a novel multi-direction weighted TV(MDWTV)model is proposed based on multi-direction edge detection.Moreover,combing with the dark channel prior and MDWTV this paper present a blind image deblurring method with more capacity of detail recovery and more applicability in various scenarios.At the same time,a kernel estimation method is addressed based on adaptive strong edge extraction which can remove fake edges and noise as well as increase the robustness of kernel estimation.Then a modified alternating direction method(ADM)is proposed to solve the above model.Extensive experimental results show that our method can esti-mate the blur kernel more accurately,and the restored image contains more details such as edge and texture.In the field of image non blind deblurring,in order to overcome the limitations of traditional TV regularization in image restoration with the deficient ability of detail recovery and sensitivity to the noise,the total generalized variation is applied into image deblurring.And an adaptive weighted TGV image deblurring model is proposed.This model can adaptively adjust the weights according to the local image structure,avoid the staircase effect while preserving the edges of the image and suppress the noise.In order to solve the proposed model,the Primal-Dual algorithm for Adaptive Weighted TGV is proposed based on Primal-Dual algorithm.Extensive experimental results show that our method can obtain high quality recovery images and the solving algorithm has low time complexity and fast solving speed.