Fast image deconvolution using Hyper-Laplacian Prior Dilip Krishnan Rob Fergus New york University Presented by Zhengming Xing
Outline Introduction Algorithm Experiment result
introduction Hyper-Laplacian Prior speed
algorithm For non-blind deconvolution problem Given y (the blurred image), and k( blur kernel), x(original image). Assume Gaussian noise. Hyper-Laplacain prior Minimize
Optimize problem recall Half quadratic penalty method, introduce auxiliary variable.And consider the one special case.
Solve sub-problem Recall: Fixed w
Solve sub-problem Fixed X Recall: Lookup table: pre-compute solution for different Analytic solution: for particular value of
Recall: Take derivative Compare the different root and find the global minimum
Summary of the algorithm
Summary of the algorithm
Experiment description Grey scale real world image, blurred by camera shaked kernels and add Gaussian noise. The kernels are minor perturbed. Measured with the SNR
result
result
result