Efficient O(1) edge-aware filter

In this paper, we propose an exact and efficient O(1) edge-aware filter. Starting from the generic 1D weighted average filter, by enforcing two assumptions on the filter kernel, we derive the fast O(1) algorithm to exactly implement the filter by two pass recursions. Performing the 1D filter horizontally and vertically can easily extend it to 2D case. A typical real valued geodesic kernel and a novel complex valued bilateral-like kernel are investigated in our proposed filtering framework. Experiments show that both kernels work well for the edge-aware smoothing task, and the bilateral-like kernel based filter shows the similar ability as the guided filter in the image feathering application.