Efficient structured parsing of facades using dynamic programming

Andrea Cohen; Alexander Gerhard Schwing; Marc Pollefeys

doi:10.1109/CVPR.2014.410

Efficient structured parsing of facades using dynamic programming

Andrea Cohen, Alexander Gerhard Schwing, Marc Pollefeys

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We propose a sequential optimization technique for segmenting a rectified image of a facade into semantic categories. Our method retrieves a parsing which respects common architectural constraints and also returns a certificate for global optimality. Contrasting the suggested method, the considered facade labeling problem is typically tackled as a classification task or as grammar parsing. Both approaches are not capable of fully exploiting the regularity of the problem. Therefore, our technique very significantly improves the accuracy compared to the state-of-the-art while being an order of magnitude faster. In addition, in 85% of the test images we obtain a certificate for optimality.

Original language	English (US)
Title of host publication	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher	IEEE Computer Society
Pages	3206-3213
Number of pages	8
ISBN (Electronic)	9781479951178, 9781479951178
DOIs	https://doi.org/10.1109/CVPR.2014.410
State	Published - Sep 24 2014
Externally published	Yes
Event	27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States Duration: Jun 23 2014 → Jun 28 2014

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)	1063-6919

Other

Other	27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Country/Territory	United States
City	Columbus
Period	6/23/14 → 6/28/14

Keywords

dynamic programming
facade parsing
structured segmentation
urban scene understanding

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Online availability

10.1109/CVPR.2014.410

Library availability

Discover UIUC Full Text

Cite this

Cohen, A., Schwing, A. G., & Pollefeys, M. (2014). Efficient structured parsing of facades using dynamic programming. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 3206-3213). [6909806] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE Computer Society. https://doi.org/10.1109/CVPR.2014.410

Efficient structured parsing of facades using dynamic programming. / Cohen, Andrea; Schwing, Alexander Gerhard; Pollefeys, Marc.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2014. p. 3206-3213 6909806 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Cohen, A, Schwing, AG & Pollefeys, M 2014, Efficient structured parsing of facades using dynamic programming. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 6909806, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, pp. 3206-3213, 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, United States, 6/23/14. https://doi.org/10.1109/CVPR.2014.410

Cohen A, Schwing AG, Pollefeys M. Efficient structured parsing of facades using dynamic programming. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society. 2014. p. 3206-3213. 6909806. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). doi: 10.1109/CVPR.2014.410

@inproceedings{064195810ae848f48864ce5c3caf54aa,

title = "Efficient structured parsing of facades using dynamic programming",

abstract = "We propose a sequential optimization technique for segmenting a rectified image of a facade into semantic categories. Our method retrieves a parsing which respects common architectural constraints and also returns a certificate for global optimality. Contrasting the suggested method, the considered facade labeling problem is typically tackled as a classification task or as grammar parsing. Both approaches are not capable of fully exploiting the regularity of the problem. Therefore, our technique very significantly improves the accuracy compared to the state-of-the-art while being an order of magnitude faster. In addition, in 85% of the test images we obtain a certificate for optimality.",

keywords = "dynamic programming, facade parsing, structured segmentation, urban scene understanding",

author = "Andrea Cohen and Schwing, {Alexander Gerhard} and Marc Pollefeys",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 ; Conference date: 23-06-2014 Through 28-06-2014",

year = "2014",

month = sep,

day = "24",

doi = "10.1109/CVPR.2014.410",

language = "English (US)",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "3206--3213",

booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - Efficient structured parsing of facades using dynamic programming

AU - Cohen, Andrea

AU - Schwing, Alexander Gerhard

AU - Pollefeys, Marc

PY - 2014/9/24

Y1 - 2014/9/24

N2 - We propose a sequential optimization technique for segmenting a rectified image of a facade into semantic categories. Our method retrieves a parsing which respects common architectural constraints and also returns a certificate for global optimality. Contrasting the suggested method, the considered facade labeling problem is typically tackled as a classification task or as grammar parsing. Both approaches are not capable of fully exploiting the regularity of the problem. Therefore, our technique very significantly improves the accuracy compared to the state-of-the-art while being an order of magnitude faster. In addition, in 85% of the test images we obtain a certificate for optimality.

AB - We propose a sequential optimization technique for segmenting a rectified image of a facade into semantic categories. Our method retrieves a parsing which respects common architectural constraints and also returns a certificate for global optimality. Contrasting the suggested method, the considered facade labeling problem is typically tackled as a classification task or as grammar parsing. Both approaches are not capable of fully exploiting the regularity of the problem. Therefore, our technique very significantly improves the accuracy compared to the state-of-the-art while being an order of magnitude faster. In addition, in 85% of the test images we obtain a certificate for optimality.

KW - dynamic programming

KW - facade parsing

KW - structured segmentation

KW - urban scene understanding

UR - http://www.scopus.com/inward/record.url?scp=84911407048&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84911407048&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2014.410

DO - 10.1109/CVPR.2014.410

M3 - Conference contribution

AN - SCOPUS:84911407048

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 3206

EP - 3213

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

PB - IEEE Computer Society

T2 - 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014

Y2 - 23 June 2014 through 28 June 2014

ER -

Efficient structured parsing of facades using dynamic programming

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this