A MRF Shape Prior for Facade Parsing with Occlusions
Abstract
We present a new shape prior formalism for the segmentation of rectified 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 finding 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 efficient 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.
Fichier principal
Kozinski_A_MRF_Shape_2015_CVPR_paper.pdf (7.45 Mo)
Télécharger le fichier
CVPR-2015-Kozinski-et-al_supp.pdf (182.25 Ko)
Télécharger le fichier
Origin : Explicit agreement for this submission
Format : Short paper
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)
Loading...