On Neighbourhood Matching for Texture-by-Numbers
| dc.contributor.author | Sivaks, Eliyahu | en_US |
| dc.contributor.author | Lischinski, Dani | en_US |
| dc.contributor.editor | Eduard Groeller and Holly Rushmeier | en_US |
| dc.date.accessioned | 2015-02-27T10:19:11Z | |
| dc.date.available | 2015-02-27T10:19:11Z | |
| dc.date.issued | 2011 | en_US |
| dc.description.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. | en_US |
| dc.description.number | 1 | |
| dc.description.seriesinformation | Computer Graphics Forum | en_US |
| dc.description.volume | 30 | |
| dc.identifier.doi | 10.1111/j.1467-8659.2010.01837.x | en_US |
| dc.identifier.issn | 1467-8659 | en_US |
| dc.identifier.uri | https://doi.org/10.1111/j.1467-8659.2010.01837.x | en_US |
| dc.publisher | The Eurographics Association and Blackwell Publishing Ltd. | en_US |
| dc.title | On Neighbourhood Matching for Texture-by-Numbers | en_US |