Removing out-of-focus blur from a single image
This work provides a practical solution for applications like digital photography and robotics, but it is incremental as it builds on existing defocus map estimators.
The paper tackled the problem of removing out-of-focus blur from a single image by proposing a blind deconvolution method that addresses segmentation artifacts and improves kernel estimation, showing advantages over existing methods in experiments on real datasets.
Reproducing an all-in-focus image from an image with defocus regions is of practical value in many applications, eg, digital photography, and robotics. Using the output of some existing defocus map estimator, existing approaches first segment a de-focused image into multiple regions blurred by Gaussian kernels with different variance each, and then de-blur each region using the corresponding Gaussian kernel. In this paper, we proposed a blind deconvolution method specifically designed for removing defocus blurring from an image, by providing effective solutions to two critical problems: 1) suppressing the artifacts caused by segmentation error by introducing an additional variable regularized by weighted $\ell_0$-norm; and 2) more accurate defocus kernel estimation using non-parametric symmetry and low-rank based constraints on the kernel. The experiments on real datasets showed the advantages of the proposed method over existing ones, thanks to the effective treatments of the two important issues mentioned above during deconvolution.