Four-Directional Total Variation With Overlapping Group Sparsity for Image Denosing

In this paper, a new model combining four-directional total variation with overlapping group sparsity is proposed, which not only suppresses the staircase effects introduced by traditional variation, but also fully utilizes gradient neighborhood information on each pixel of image. order to decrease computation time image denoising, alternating direction method multipliers (ADMM) adopted divide complex optimization problem into separate subproblems that are easy solve. At same time, two-dimensional Fast Fourier Transform (FFT) and majorization-minimization (MM) used solve alternatively. Then, proposed compared other state-of-the-art models. Experiments show robust in denoising. The excavates four directions remove noise more effectively, better preserving features, further reducing artifacts.