Blind Image Deblurring Using Dark Channel Prior

Citation:

Pan J, Sun D, Yang M-H, Pfister H. Blind Image Deblurring Using Dark Channel Prior. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016. 2016
Blind Image Deblurring Using Dark Channel Prior

Abstract:

 
Abstract
We present a simple and effective blind image deblur-
ring method based on the dark channel prior. Our work is
inspired by the interesting observation that the dark chan-
nel of blurred images is less sparse. While most image
patches in the clean image contain some dark pixels, these
pixels are not dark when averaged with neighboring high-
intensity pixels during the blur process. This change in the
sparsity of the dark channel is an inherent property of the
blur process, which we both prove mathematically and val-
idate using training data. Therefore, enforcing the sparsity
of the dark channel helps blind deblurring on various sce-
narios, including natural, face, text, and low-illumination
images. However, sparsity of the dark channel introduces
a non-convex non-linear optimization problem. We intro-
duce a linear approximation of the
min
operator to com-
pute the dark channel. Our look-up-table-based method
converges fast in practice and can be directly extended to
non-uniform deblurring. Extensive experiments show that
our method achieves state-of-the-art results on deblurring
natural images and compares favorably methods that are
well-engineered for specific scenarios.

Last updated on 10/20/2016