A MAP framework for single-image deblurring based on sparse priors

Blind image restoration is a typically ill-posed problem, many methods tend to construct the loss function using the latent image and blur kernel priors. In this paper, we propose a MAP framework for single image motion deblurring by introducing a constrained regularization of approximate L0 and L1 sparsity respectively for latent image and motion kernel, and the optimization is conducted by fast numerical approaches. The proposed scheme is shown to be robust and effective by the experiments on both synthesized and real images. The results and comparisons to the state-of-the-art methods will be displayed.