Total variation with overlapping group sparsity for image deblurring under impulse noise
This is an incremental improvement for image processing applications, addressing specific artifacts in deblurring tasks.
The authors tackled image deblurring under impulse noise by proposing a model combining total variation with overlapping group sparsity to reduce staircase effects, resulting in improved restoration quality as measured by PSNR and relative error.
The total variation (TV) regularization method is an effective method for image deblurring in preserving edges. However, the TV based solutions usually have some staircase effects. In this paper, in order to alleviate the staircase effect, we propose a new model for restoring blurred images with impulse noise. The model consists of an $\ell_1$-fidelity term and a TV with overlapping group sparsity (OGS) regularization term. Moreover, we impose a box constraint to the proposed model for getting more accurate solutions. An efficient and effective algorithm is proposed to solve the model under the framework of the alternating direction method of multipliers (ADMM). We use an inner loop which is nested inside the majorization minimization (MM) iteration for the subproblem of the proposed method. Compared with other methods, numerical results illustrate that the proposed method, can significantly improve the restoration quality, both in avoiding staircase effects and in terms of peak signal-to-noise ratio (PSNR) and relative error (ReE).