ETH Zurich - D-INFK - IVC - CVG - Research - Facade parsing using DP

Efficient Structured Parsing of Facades Using Dynamic Programming


teaser

Andrea Cohen
ETH Zürich, Switzerland
acohen@inf.ethz.ch
Alexander G. Schwing
University of Toronto, Canada
aschwing@cs.toronto.edu
Marc Pollefeys
ETH Zürich, Switzerland
marc.pollefeys@inf.ethz.ch

IEEE Int. Conf. on Computer Vision and Pattern Recognition 2014

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.

Publication

  • Efficient Structured Parsing of Façades Using Dynamic Programming,
    A. Cohen, A. Schwing, M. Pollefeys.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2014
    [PDF] [Video] [bibtex]
    @InProceedings{Cohen_2014_CVPR,
    author = {Andrea Cohen and Alexander G. Schwing and Marc Pollefeys},
    title = {Efficient Structured Parsing of Facades Using Dynamic Programming},
    journal = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    location = {Columbus, OH, USA},
    month = {June},
    year = {2014},
    }

  • Results

    ECP dataset

    ecp

    The original dataset can be found on http://vision.mas.ecp.fr/Personnel/teboul/data.php. We use the annotations provided by http://homes.esat.kuleuven.be/~amartino/datasets/ECP_newAnnotations.zip.

    eTrims dataset

    etrims

    The original dataset can be found on http://www.ipb.uni-bonn.de/projects/etrims_db/.

    Miscellaneous dataset

    misc

    This dataset is composed by different images from facades from all around the world. Most of them can be found at http://vision.mas.ecp.fr/Personnel/teboul/data.php. A compilation of all this images can be downloaded [here]. Another part of this dataset consists of a selection of rectified images from the ZuBud dataset. These rectified images can be found [here].


    © CVG, ETH Zürich lm@inf.ethz.ch