Abstract
Blind image deblurring is a well-known conundrum in the digital image processing field. To get a solid and pleasing deblurred result, reasonable statistical prior of the true image and the blur kernel is required. In this work, a novel and efficient blind image deblurring method which utilizes the Local Maximum Difference Prior ( LMD ) is presented. We find that the maximum value of the sum of the differences between the intensity of one pixel and its surrounding 8 pixels in the local image patch becomes smaller with motion blur. This phenomenon is an intrinsic feature of the motion blur process, we demonstrate it theoretically in this paper. By introducing a linear operator to compute LMD and adopting the $L_{1} $ norm constrain to the LMD involved term, an effective optimization scheme which makes use of a half-quadratic splitting strategy is exploited. Experimental results show that the presented method is more robust and outperforms the most advanced deblurring methods on both composite images and ground-truth scenes. Besides, this algorithm is more general because it does not require any heuristic edge selection steps or need too many extreme value pixels in the input image.
Highlights
The task of image deblurring is to obtain a clear image from a blurred measurement, which is a hot and famous topic [2]
When the blur kernel k is unknown, it becomes a classical ill-conditioned problem to obtain a clear image from the model (1)
By enforcing the L1 norm constrain to the Local Maximum Difference Prior (LMD) involved term and the L0 norm constrain to the gradient involved term, we present a valid optimization scheme
Summary
The task of image deblurring is to obtain a clear image from a blurred measurement, which is a hot and famous topic [2]. Among them are heavy-tailed distribution of the gradient [5], L1 L2 prior [14], L0 gradient [22], patch-based prior [29], color-line prior [31], dark channel prior [35], low-rank prior [36], extreme channel prior [41] and local maximum gradient prior [46], just to name a few These methods perform well, there is still room for improvement. We find an interesting phenomenon: the maximum value of the sum of the differences between the intensity of one pixel and its surrounding 8 pixels in the local image patch will decrease with the blurring process. Our approach performs favorably on both composite images [9], [19], [26], [34] and ground-truth images [34] against the most advanced approaches
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.