Deblurring of Poissonian images using BM3D frames

We propose a novel deblurring algorithm for Poissonian images. The algorithm uses data adaptive BM3D-frames for sparse image modeling. Reconstruction is formulated as a generalized Nash equilibrium problem, seeking a balance between the data fit and the complexity of the solution. Simulated experiments demonstrate numerical and visual superiority of the proposed algorithm over the current state-of-the-art methods.