Parallelization of a Blind Deconvolution Algorithm (Postprint)

摘要

Often it is of interest to deblur imagery in order to obtain higher- resolution images. Deblurring requires knowledge of the blurring function - information that is often not available separately from the blurred imagery. Blind deconvolution algorithms overcome this problem by jointly estimating both the high-resolution image and the blurring function from the blurred imagery. Because blind deconvolution algorithms are iterative in nature, they can take minutes to days to deblur an image depending on how many frames of date are used for the deblurring and the platforms on which the algorithms are executed. Here we present our progress in parallelizing a blind deconvolution algorithm to increase its executions speed. This progress includes sub-frame parallelization and a code structure that is not specialized to a specific computer hardware architecture.