TY - GEN
T1 - Parsing façade with rank-one approximation
AU - Yang, Chao
AU - Han, Tian
AU - Quan, Long
AU - Tai, Chiew Lan
PY - 2012
Y1 - 2012
N2 - The binary split grammar is powerful to parse façade in a broad range of types, whose structure is characterized by repetitive patterns with different layouts. We notice that, as far as two labels are concerned, BSG parsing is equivalent to approximating a façade by a matrix with multiple rank-one patterns. Then, we propose an efficient algorithm to decompose an arbitrary matrix into a rank-one matrix and a residual matrix, whose magnitude is small in the sense of l 0-norm. Next, we develop a block-wise partition method to parse a more general façade. Our method leverages on the recent breakthroughs in convex optimization that can effectively decompose a matrix into a low-rank and sparse matrix pair. The rank-one block-wise parsing not only leads to the detection of repetitive patterns, but also gives an accurate façade segmentation. Experiments on intensive façade data sets have demonstrated that our method outperforms the state-of-the-art techniques and benchmarks both in robustness and efficiency.
AB - The binary split grammar is powerful to parse façade in a broad range of types, whose structure is characterized by repetitive patterns with different layouts. We notice that, as far as two labels are concerned, BSG parsing is equivalent to approximating a façade by a matrix with multiple rank-one patterns. Then, we propose an efficient algorithm to decompose an arbitrary matrix into a rank-one matrix and a residual matrix, whose magnitude is small in the sense of l 0-norm. Next, we develop a block-wise partition method to parse a more general façade. Our method leverages on the recent breakthroughs in convex optimization that can effectively decompose a matrix into a low-rank and sparse matrix pair. The rank-one block-wise parsing not only leads to the detection of repetitive patterns, but also gives an accurate façade segmentation. Experiments on intensive façade data sets have demonstrated that our method outperforms the state-of-the-art techniques and benchmarks both in robustness and efficiency.
UR - http://www.scopus.com/inward/record.url?scp=84866697250&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84866697250&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2012.6247867
DO - 10.1109/CVPR.2012.6247867
M3 - Conference contribution
AN - SCOPUS:84866697250
SN - 9781467312264
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1720
EP - 1727
BT - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
T2 - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Y2 - 16 June 2012 through 21 June 2012
ER -