Motion blur kernel estimation via salient edges and low rank prior

Blind image deblurring, i.e., estimating a blur kernel from a single input blurred image is a severely ill-posed problem. In this paper, we show how to effectively apply low rank prior to blind image deblurring and then propose a new algorithm which combines salient edges and low rank prior. Salient edges provide reliable edge information for kernel estimation, while low rank prior provides data-authentic priors for the latent image. When estimating the kernel, the salient edges are extracted from an intermediate latent image solved by combining the predicted edges and low rank prior, which help preserve more useful edges than previous deconvolution methods do. By solving the blind image deblurring problem in this fashion, high-quality blur kernels can be obtained. Extensive experiments testify to the superiority of the proposed method over state-of-the-art algorithms, both qualitatively and quantitatively.