Skip to Main Content
Super-resolution is the process of obtaining a high resolution image from multiple low resolution images. In most of the super-resolution algorithms, the blur parameter of a LR-image model always have to be manually set as a default value, this is not a good solution. In this paper, we propose a method which can adaptively estimate the blur parameter. Fusing all low-resolution images, we will get the initial image. When it is used in MAP algorithm, no more than 10 iterations is sufficient to get a stable solution. Compared with other MAP algorithms, this algorithm can greatly reduce the computation demand. Experiments show that when is applied to real image sequences, it can preserve the image edges and details. and the reconstructed image is clear. The propose algorithm is very different.