A L_0 sparse analysis prior for blind poissonian image deconvolution

This paper proposes a new approach for blindly deconvolving images that are contaminated by Poisson noise. The proposed approach incorporates a new prior, that is the L0 sparse analysis prior, together with the total variation constraint into the maximum a posteriori (MAP) framework for deconvolution. A greedy analysis pursuit numerical scheme is exploited to solve the L0 regularized MAP problem. Experimental results show that our approach not only produces smooth results substantially suppressing artifacts and noise, but also preserves intensity changes sharply. Both quantitative and qualitative comparisons to the specialized state-of-the-art algorithms demonstrate its superiority.