A blind motion deblurring for daytime and nighttime images

This paper presents an automatic deblurring approach for motion blur images. The approach explores the prior of the intensity and gradient to estimate the motion blur kernel from single blurred image. In this way, motion blur kernel could be well estimated not only on daytime images, but also on nighttime images. Efficient optimization method was given for the prior-based approach. Besides, a cost-effective method was also proposed to remove the noise of the kernel in the iterative kernel estimation. The proposed kernel enhancement approach could also improve the performance of other blind deblurring algorithm. Experimental results showed that the performance of the proposed algorithm was superior to many state-of-the-art blind deblurring algorithms, especially for nighttime images with saturated regions.