Fast $\ell ^{0}$ -Regularized Kernel Estimation for Robust Motion Deblurring

Blind image deblurring is a challenging problem in computer vision and image processing. In this paper, we propose a new l⁰-regularized approach to estimate a blur kernel from a single blurred image by regularizing the sparsity property of natural images. Furthermore, by introducing an adaptive structure map in the deblurring process, our method is able to restore useful salient edges for kernel estimation. Finally, we propose an efficient algorithm which can solve the proposed model efficiently. Extensive experiments compared with state-of-the-art blind deblurring methods demonstrate the effectiveness of the proposed method.