Efficient image deblurring via blockwise non-blind deconvolution algorithm

Image deblurring aims to restore the quality of degraded images and plays an important role in many multimedia applications. Implementing a deblurring algorithm directly, however, is usually computationally expensive, especially for high-resolution images. In this paper, we propose to first partition the image in blocks (sub-images) and then implement the deblurring algorithm on a block basis for deblurring high-resolution or large-dimension images. Overlap regions among blocks are linearly filtered to reduce the distortion at the edge due to the block-based implementation. Simulations demonstrate that the proposed method achieves satisfactory result with much less computation time.