Title
Example-Based Facade Texture Synthesis
Abstract
There is an increased interest in the efficient creation of city models, be it virtual or as-built. We present a method for synthesizing complex, photo-realistic facade images, from a single example. After parsing the example image into its semantic components, a tiling for it is generated. Novel tilings can then be created, yielding facade textures with different dimensions or with occluded parts in painted. A genetic algorithm guides the novel facades as well as in painted parts to be consistent with the example, both in terms of their overall structure and their detailed textures. Promising results for multiple standard datasets - in particular for the different building styles they contain - demonstrate the potential of the method.
Year
DOI
Venue
2013
10.1109/ICCV.2013.136
ICCV
Keywords
Field
DocType
facade inpainting,multiple standard datasets,example image,painted part,facade texture synthesis,novel facade,different dimension,different building style,example-based facade texture synthesis,single example,photo-realistic facade image,building styles,photo-realistic facade images,signal synthesis,genetic algorithm,city model,genetic algorithms,facade texture,facade modeling,facade parsing,semantic components,image texture,buildings (structures),novel tilings,city models
Computer vision,Pattern recognition,Computer science,Image texture,Artificial intelligence,Signal synthesis,Facade,Parsing,Texture synthesis,Genetic algorithm,Facade pattern
Conference
Volume
Issue
ISSN
2013
1
1550-5499
Citations 
PageRank 
References 
10
0.50
25
Authors
4
Name
Order
Citations
PageRank
Dengxin Dai142335.20
Hayko Riemenschneider233518.19
Gerhard Schmitt312211.98
Luc Van Gool4275661819.51