Towards effective evaluation of geometric texture synthesis algorithms

AlMeraj, Zainab; Kaplan, Craig S.; Asente, Paul

Towards effective evaluation of geometric texture synthesis algorithms

Files

005-014.pdf (8.26 MB)

005-09.pdf (31.12 KB)

Date

2013

Authors

AlMeraj, Zainab
Kaplan, Craig S.
Asente, Paul

Publisher

ACM

Abstract

In recent years, an increasing number of example-based Geometric Texture Synthesis (GTS) algorithms have been proposed. However, there have been few attempts to evaluate these algorithms rigorously. We are driven by this lack of validation and the simplicity of the GTS problem to look closer at perceptual similarity between geometric arrangements. Using samples from a geological database, our research first establishes a dataset of geometric arrangements gathered from multiple synthesis sources. We then employ the dataset in two evaluation studies. Collectively these empirical methods provide formal foundations for perceptual studies in GTS, insight into the robustness of GTS algorithms and a better understanding of similarity in the context of geometric texture arrangements.

        @inproceedings{10.1145:2486042.2486043
,
booktitle = {International Symposium on Non-Photorealistic Animation and Rendering
},
editor = {Forrester Cole and Cindy Grimm
},
title = {{Towards effective evaluation of geometric texture synthesis algorithms
}},
author = {AlMeraj, Zainab and 
Kaplan, Craig S. and 
Asente, Paul
},
year = {2013
},
publisher = {ACM
},
ISBN = {978-1-4503-2198-3
},
DOI = {10.1145/2486042.2486043
}
}