Roof-edge preserving image smoothing based on MRFs

A novel Markov random field (MRF) model is proposed for roof-edge (as well as step-edge) preserving image smoothing. Image surfaces containing roof-edges are represented by piecewise continuous polynomial functions governed by a few parameters. Piecewise smoothness constraint is imposed on these parameters rather than on the surface heights as is in traditional models for step-edges. In this way, roof edges are preserved without the necessity to deal with unstable higher order derivatives.