Edge-Aware Filter Based on Adaptive Patch Variance Weighted Average

Edge-aware smoothing is an essential tool for computer vision, graphics and photography. In this paper, we develop a new efficient local weighted average filter edge-aware smoothing. The proposed can use guidance information which permits iterative filtering process. Since the weights of depend on variance, implementation requires linear filters only, leading to $\mathcal {O}(N_{pix})$ computational complexity. We also present statistical analysis simulations provide insights into its efficiency relationship with bilateral filter. performance comparable those state-of-the-art in many applications including: edge-preserving smoothing, compression artifact removal, structure separation, edge extraction, non-photo realistic image rendering, salience detection, detail magnification multi-focus fusion.