TY - GEN
T1 - A MRF shape prior for facade parsing with occlusions
AU - Koziński, Mateusz
AU - Gadde, Raghudeep
AU - Zagoruyko, Sergey
AU - Obozinski, Guillaume
AU - Marlet, Renaud
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/10/14
Y1 - 2015/10/14
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/84959251293
U2 - 10.1109/CVPR.2015.7298899
DO - 10.1109/CVPR.2015.7298899
M3 - Conference contribution
AN - SCOPUS:84959251293
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 2820
EP - 2828
BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
PB - IEEE Computer Society
T2 - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Y2 - 7 June 2015 through 12 June 2015
ER -