Show simple item record

dc.contributor.authorAlsisan, Suhiben_US
dc.contributor.authorMitra, Niloy J.en_US
dc.contributor.editorCarlos Andujar and Enrico Puppoen_US
dc.date.accessioned2013-11-08T10:28:37Z
dc.date.available2013-11-08T10:28:37Z
dc.date.issued2012en_US
dc.identifier.issn1017-4656en_US
dc.identifier.urihttp://dx.doi.org/10.2312/conf/EG2012/short/037-040en_US
dc.description.abstractUrban facades contain large-scale repetitions in the form of windows, doors, etc. Such elements often are in different configurations (e.g., open or closed) obscuring their regular arrangements to any direct low-level pixel matching based repetition detection.We propose a variation-factored representation for facade images by progressively favoring larger repeated structures while allowing relabeling using candidate element types. We formulate the problem as a Markov Random Field (MRF) based optimization, and evaluate the algorithm on a large number of benchmark facade images. Such a facade encoding is very compact and can be used for rapid generation of realistic 3D models with variations suitable for online map viewers or mobile navigation aids.en_US
dc.publisherThe Eurographics Associationen_US
dc.titleVariation-Factored Encoding of Facade Imagesen_US
dc.description.seriesinformationEurographics 2012 - Short Papersen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record