Efficient Structured Parsing of Facades Using Dynamic Programming

Andrea Cohen, Alexander G. Schwing, Marc Pollefeys

CVPR 2014

doi:10.1109/CVPR.2014.410 /cvpr/2014/cohen2014cvpr-efficient/

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.

PDF CVPR Semantic Scholar

Cite

Text

Cohen et al. "Efficient Structured Parsing of Facades Using Dynamic Programming." Conference on Computer Vision and Pattern Recognition, 2014. doi:10.1109/CVPR.2014.410

Markdown

[Cohen et al. "Efficient Structured Parsing of Facades Using Dynamic Programming." Conference on Computer Vision and Pattern Recognition, 2014.](https://mlanthology.org/cvpr/2014/cohen2014cvpr-efficient/) doi:10.1109/CVPR.2014.410

BibTeX

@inproceedings{cohen2014cvpr-efficient,
  title     = {{Efficient Structured Parsing of Facades Using Dynamic Programming}},
  author    = {Cohen, Andrea and Schwing, Alexander G. and Pollefeys, Marc},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2014},
  doi       = {10.1109/CVPR.2014.410},
  url       = {https://mlanthology.org/cvpr/2014/cohen2014cvpr-efficient/}
}