Abstract
We present a new shape prior formalism for the segmentation of rectifified facade images. It combines the simplicity of split grammars with unprecedented expressive power: the capability of encoding simultaneous alignment in two dimensions, facade occlusions and irregular boundaries between facade elements. We formulate the task of fifinding the most likely image segmentation conforming to a prior of the proposed form as a MAP-MRF problem over a 4-connected pixel grid, and propose an effificient optimization algorithm for solving it. Our method simultaneously segments the visible and occluding objects, and recovers the structure of the occluded facade. We demonstrate state-of-the-art results on a number of facade segmentation datasets.