Super-Resolution Using Adaptive Blur Parameter Estimation

Super-resolution is a term for a set of methods of increasing image or video resolution. All these methods are based on the same idea: using information from several images to create one upsized image. In most of the super-resolution algorithms, the blur parameter of a LR-image model is always manually set as a default value. In this paper, we propose a method to adaptively estimate the blur parameter. We get the initial image of iteration by fusing all low-resolution images .When it is used in MAP algorithm, three iterations are enough to get a stable solution. It is greatly reduce the computational power compared with other MAP algorithms. Experiments to real image sequences show that it well preserved the image detail and the reconstructed image is clear.