Fast Blind Image Deblurring Using Smoothing-Enhancing Regularizer

Blind deconvolution is a highly ill-posed problem for the restoration of degraded images and requires prior knowledge or regularization. Recently, various priors have been proposed and the models based on these priors have achieved state-of-the-art performances. In this paper, we present a blind image deblurring method based on a computationally efficient and effective image regularizer. The proposed regularizer is motivated by the fact that the success of recent priors mainly stems from their properties, which implicitly generate an unnatural latent image suppressing insignificant structures and preserving only salient edges. These salient edges guide the models to estimate an accurate kernel. In this paper, the proposed regularizer termed smoothing-enhancing regularizer, not only assures that only salient structures in the image are preserved but also enhances these salient structures to help the model estimate the more accurate kernel. To efficiently solve the proposed model, we develop an efficient numerical approach based on the half-quadratic splitting algorithm and the lagged-fixed-point iteration scheme. The optimization scheme only requires a few additional shrinkage operations compared with the original half-quadratic splitting algorithm, making our method much faster than recent leading methods. The qualitative and quantitative experimental results show that our algorithm achieves the state-of-the-art results and can be extended to other challenging deblurring tasks, such as those involving text, face, and low-illuminated images. Furthermore, the proposed method is much more computationally efficient than the recent state-of-the-art algorithms with up to more than 10× faster execution time.