Publication Type : Journal Article
Publisher : International Journal of Computer Vision and Signal Processing
Source : International Journal of Computer Vision and Signal Processing, 6(1), 33-46(2016)
Keywords : architectural image based modeling, single viewreconstruction, vision and scene understanding, shape grammars,procedural modeling
Campus : Amritapuri
School : School of Engineering
Department : Computer Science
Year : 2016
Abstract : We present a novel modeling framework to generate real-world 3D build-ings from a single facade layout that adapt to the real footprint dataautomatically. Facade components are extracted from the facade lay-out and organized as a repetitive shape tree. Building facade layoutencodes expected architectural constraints and is able to derive complexinstances using shape grammars. We extend the previous approachesof procedural building models to a constraint-based framework for therecovery of the hidden parts of the building. We then provide an in-teractive editing process for updating of the structural topology given adifferent view of the building. We demonstrate our framework on severalreal-world buildings with varying amount of complexity in appearanceand footprint shape and we show that our approach can generate sim-ilar buildings to the original that are used to populate a virtual citydepicting implicit culture and style of different ages, while opening newperspectives for image understanding and 3D modeling.
Cite this Research Publication : Divya Udayan J, HyungSeok Kim, 2016, “Constrained Procedural Modeling of Real Buildings from Single Facade Layout”, International Journal of Computer Vision and Signal Processing, 6(1), pp: 33-46, (SCOPUS Index)