TY - JOUR
T1 - Stochastic Blind Motion Deblurring
AU - Xiao, Lei
AU - Gregson, James
AU - Heide, Felix
AU - Heidrich, Wolfgang
N1 - KAUST Repository Item: Exported on 2020-10-01
PY - 2015/5/13
Y1 - 2015/5/13
N2 - Blind motion deblurring from a single image is a highly under-constrained problem with many degenerate solutions. A good approximation of the intrinsic image can therefore only be obtained with the help of prior information in the form of (often non-convex) regularization terms for both the intrinsic image and the kernel. While the best choice of image priors is still a topic of ongoing investigation, this research is made more complicated by the fact that historically each new prior requires the development of a custom optimization method. In this paper, we develop a stochastic optimization method for blind deconvolution. Since this stochastic solver does not require the explicit computation of the gradient of the objective function and uses only efficient local evaluation of the objective, new priors can be implemented and tested very quickly. We demonstrate that this framework, in combination with different image priors produces results with PSNR values that match or exceed the results obtained by much more complex state-of-the-art blind motion deblurring algorithms.
AB - Blind motion deblurring from a single image is a highly under-constrained problem with many degenerate solutions. A good approximation of the intrinsic image can therefore only be obtained with the help of prior information in the form of (often non-convex) regularization terms for both the intrinsic image and the kernel. While the best choice of image priors is still a topic of ongoing investigation, this research is made more complicated by the fact that historically each new prior requires the development of a custom optimization method. In this paper, we develop a stochastic optimization method for blind deconvolution. Since this stochastic solver does not require the explicit computation of the gradient of the objective function and uses only efficient local evaluation of the objective, new priors can be implemented and tested very quickly. We demonstrate that this framework, in combination with different image priors produces results with PSNR values that match or exceed the results obtained by much more complex state-of-the-art blind motion deblurring algorithms.
UR - http://hdl.handle.net/10754/556419
UR - http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7106534
UR - http://www.scopus.com/inward/record.url?scp=84933056689&partnerID=8YFLogxK
U2 - 10.1109/TIP.2015.2432716
DO - 10.1109/TIP.2015.2432716
M3 - Article
SN - 1057-7149
VL - 24
SP - 3071
EP - 3085
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
IS - 10
ER -