Fast MAP-based multiframe super-resolution image reconstruction

Super-resolution image reconstruction produces a high-resolution image from a set of shifted, blurred, and decimated versions thereof. Previously published papers have not addressed the computational complexity of this ill-conditioned large scale problem adequately. In this paper, the computational complexity of MAP-based multiframe super-resolution algorithms is studied, and a new fast algorithm, as well as methods for parallel image reconstruction is also presented. The proposed fast algorithm splits the multiple input low-resolution images into several subsets according to their translation relations, and then applies normal MAP algorithm to each subset, the reconstructed images are processed subsequently at a successive level until the desired resolution is achieved. Experiment results are also provided to demonstrate the efficiency of the proposed techniques.