Paper-1: Efficient Facade Segmentation using Auto Context

Authors: Varun Jampani*, Raghudeep Gadde* and Peter V. Gehler (*equal contribution)

Abstract: In this paper we propose a system for the problem of facade segmentation. Building facades are highly structured images and consequently most methods that have been proposed for this problem, aim to make use of this strong prior information. We are describing a system that is almost domain independent and consists of standard segmentation methods. A sequence of boosted decision trees is stacked using auto-context features and learned using the stacked generalization technique. We find that this, albeit standard, technique performs better, or equals, all previous published empirical results on all available facade benchmark datasets. The proposed method is simple to implement, easy to extend, and very efficient at test time inference.

Main paper: [pdf]

Supplementary material: [pdf]

Paper-2: Efficient 2D and 3D Facade Segmentation using Auto Context

Authors: Raghudeep Gadde*, Varun Jampani*, Renaud Marlet and Peter V. Gehler (*equal contribution)

Abstract: This paper introduces a fast and efficient segmentation technique for 2D images and 3D point clouds of building facades. Facades of buildings are highly structured and consequently most methods that have been proposed for this problem aim to make use of this strong prior information. Contrary to most prior work, we are describing a system that is almost domain independent and consists of standard segmentation methods. We train a sequence of boosted decision trees using auto-context features. This is learned using stacked generalization. We find that this technique performs better, or comparable with all previous published methods and present empirical results on all available 2D and 3D facade benchmark datasets. The proposed method is simple to implement, easy to extend, and very efficient at test-time inference.

arXiv preprint: [pdf]

Datasets

Facade Segmentation Benchmarks

• ECP Dataset [1]: This prominent dataset consists of 104 Hausmannian architectural buildings from Paris. There are seven semantic classes in this dataset. 

• Graz Dataset [2]: Has 50 facade images of various architectures (Classicims, Biedermeier, Historicism, Art Noveau) from buildings in Graz. There are 4 semantic classes in this dataset.

• eTRIMS Dataset [3]: Consists of 60 non-rectified facade images which are more irregular and follow only weak architectural principles. Can be accessed here: url.

• CMP Dataset [4]: Has 378 rectified facades of diverse styles and 12 semantic classes in its base set. Can be accessed here: url.

• LabelMeFacade Dataset [5]: This consists of building facade images taken from LabelMe segmentation dataset [6]. Facades in this dataset are highly irregular with lot of diversity across images.

References:

1. Teboul, O. Ecole centrale paris facades database. 2010.
2. Riemenschneider, H., Krispel, U., Thaller, W., Donoser, M., Havemann, S., Fellner, D., & Bischof, H. Irregular lattices for complex shape grammar facade parsing. In Computer Vision and Pattern Recognition (CVPR), pp. 1640-1647, June 2012.
3. Korc, F., & Förstner, W. eTRIMS Image Database for interpreting images of man-made scenes. Dept. of Photogrammetry, University of Bonn, Tech. Rep. TRIGG-P-2009-01, April 2009.
4. Tyleček, R., & Šára, R. Spatial Pattern Templates for Recognition of Objects with Regular Structure. In Proc. of German Conference on Pattern Recognition (GCPR), pp. 364-374, 2013.
5. Frohlich, B., Rodner, E., & Denzler, J. A fast approach for pixelwise labeling of facade images. In International Conference on Pattern Recognition (ICPR), pp. 3029-3032, 2010.
6. Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. LabelMe: a database and web-based tool for image annotation. International journal of computer vision, 77(1-3), 157-173, 2008.

Code

The source code is hosted in the following bit-bucket page:

https://bitbucket.org/rgadde/wacv15_code

If you find our code or results useful for your publication, please consider citing the following works:

@inproceedings{jampani15wacv,
  title = {Efficient Facade Segmentation using Auto-Context},
  author = {Jampani, Varun and Gadde, Raghudeep and Gehler, Peter V.},
  booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
  month = jan,
  url = {http://wacv2015.org},
  year = {2015}
}

@article{gadde2016efficient,
  title={Efficient 2D and 3D Facade Segmentation using Auto-Context},
  author={Gadde, Raghudeep and Jampani, Varun and Marlet, Renaud and Gehler, Peter V},
  journal={arXiv preprint arXiv:1606.06437},
  year={2016}
}

We include the following visual results for some datasets. If your research requires other results, please contact us.

On ECP Dataset

• Folds [zip(3.6KB)]
• Visual results [zip(69MB)]

On Graz Dataset

• Folds [zip(3.1KB)]
• Visual results [zip(74MB)]

On eTRIMS Dataset

• Folds [zip(3.1KB)]
• Visual results [zip(59MB)]

On CMP Dataset

• Folds [zip(1.9KB)]

On LabelMeFacade Dataset