This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Hierarchical Co-Segmentation of Building Facades

Andelo Martinovic and Luc Van Gool
3DV 2014


We introduce a new system for automatic discovery of high-level structural representations of building facades. Under the assumption that each facade can be represented as a hierarchy of rectilinear subdivisions, our goal is to find the optimal direction of splitting, along with the number and positions of the split lines at each level of the tree. Unlike previous approaches, where each facade is analysed in isolation, we propose a joint analysis of a set of facade images. Initially, a co-segmentation approach is used to produce consistent decompositions across all facade images. Afterwards, a clustering step identifies semantically similar segments. Each cluster of similar segments is then used as the input for the joint segmentation in the next level of the hierarchy. We show that our approach produces consistent hierarchical segmentations on two different facade datasets. Furthermore, we argue that the discovered hierarchies capture essential structural information, which is demonstrated on the tasks of facade retrieval and virtual facade synthesis.

Download in pdf format
  author = {Andelo Martinovic and Luc Van Gool},
  title = {Hierarchical Co-Segmentation of Building Facades},
  booktitle = {3DV 2014},
  year = {2014},
  keywords = {}