Edge-aware smoothing through adaptive interpolation

The goal of edge-aware filtering is to smooth out small-scale structures while preserving large object boundaries. A fundamental idea to design such filters is to avoid smoothing across strong edges. In this paper, we explore a new approach which iteratively adds the edge information back to a smoothed image. We study the smoothed image as the starting point of the iteration and the optimal stopping criterion. We demonstrate that in a wide range of applications the proposed technique can produce competitive results as those of state-of-the-art edge-aware filters. In particular, the proposed algorithm has the best performance in texture smoothing.