In this letter, a new texture filter (TF) with scale- aware gradients and structural preservation is proposed. By measuring the sparsity with scale-aware gradients, and structural fidelity by H^{−1} norm with the embedded Laplacian operator, the proposed hybrid L_{0}-H^{−1} variational model smooths noise- corrupted small-scale textures with low/high contrast and pre- serves sharp and prominent structures simultaneously. Qualita- tive and quantitative experimental results demonstrate that the proposed method has a significant improvement over the state- of-the-art methods in texture filtering. Moreover, the proposed method has fast convergence.
banzheshitou/Scale-aware-Guided-and-Structure-Preserved-Texture-Filter
Scale-aware Guided and Structure Preserved Texture Filter
MATLABMIT