On Neighbourhood Matching for Texture-by-Numbers

Sivaks, Eliyahu; Lischinski, Dani

On Neighbourhood Matching for Texture-by-Numbers

Date

2011

Authors

Sivaks, Eliyahu
Lischinski, Dani

Publisher

The Eurographics Association and Blackwell Publishing Ltd.

Abstract

Texture-by-Numbers is an attractive texture synthesis framework, because it is able to cope with non-homogeneous texture exemplars, and provides the user with intuitive creative control over the outcome of the synthesis process. Like many other exemplar-based texture synthesis methods, its basic underlying mechanism is neighbourhood matching. In this paper we review a number of commonly used neighbourhood matching acceleration techniques, compare and analyse their performance in the specific context of Texture-by-Numbers (as opposed to ordinary unconstrained texture synthesis). Our study indicates that the standard approaches are not optimally suited for the Texture-by-Numbers framework, often producing visually inferior results compared to searching for the exact L2nearest neighbour. We then show that performing Texture-by-Number using the Texture Optimization framework in conjunction with an efficient FFT-based search is able to produce good results in reasonable running times and with a minimal memory overhead.

        @article{10.1111:j.1467-8659.2010.01837.x
,
journal = {Computer Graphics Forum},
title = {{On Neighbourhood Matching for Texture-by-Numbers
}},
author = {Sivaks, Eliyahu and 
Lischinski, Dani
},
year = {2011
},
publisher = {The Eurographics Association and Blackwell Publishing Ltd.
},
ISSN = {1467-8659
},
DOI = {10.1111/j.1467-8659.2010.01837.x
}
}

URI

https://doi.org/10.1111/j.1467-8659.2010.01837.x

Collections

30-Issue 1

Full item page