TY - GEN
T1 - Beyond procedural facade parsing
T2 - 12th Asian Conference on Computer Vision, ACCV 2014
AU - Koziński, Mateusz
AU - Obozinski, Guillaume
AU - Marlet, Renaud
N1 - Publisher Copyright:
© Springer International Publishing Switzerland 2015.
PY - 2015/1/1
Y1 - 2015/1/1
N2 - We propose a novel formulation for parsing facade images with user-defined shape prior. Contrary to other state-of-the-art methods, we do not explore the procedural space of shapes derived from a grammar. Instead we formulate parsing as a linear binary program which we solve using Dual Decomposition. The algorithm produces plausible approximations of globally optimal segmentations without grammar sampling. It yields state-of-the-art performance on standard datasets.
AB - We propose a novel formulation for parsing facade images with user-defined shape prior. Contrary to other state-of-the-art methods, we do not explore the procedural space of shapes derived from a grammar. Instead we formulate parsing as a linear binary program which we solve using Dual Decomposition. The algorithm produces plausible approximations of globally optimal segmentations without grammar sampling. It yields state-of-the-art performance on standard datasets.
UR - https://www.scopus.com/pages/publications/84983670640
U2 - 10.1007/978-3-319-16817-3_6
DO - 10.1007/978-3-319-16817-3_6
M3 - Conference contribution
AN - SCOPUS:84983670640
SN - 9783319168166
T3 - Lecture Notes in Computer Science
SP - 79
EP - 94
BT - ACCV 2014
PB - Springer Verlag
Y2 - 1 November 2014 through 2 November 2014
ER -