Figure 7.

Blind deconvolution of three different realistic images. From left to right: (a) input blurred image, deblurred versions generated by (b) Xu and Jia [11], (c) Krishnan et al. [9], (d) Pan et al. [59] and (e) our proposed method, respectively. The sizes of the estimated blur kernels from top to bottom are $101\times 101$, $95\times 95$ and $91\times 91$, respectively.