A Comparison Study of Four Texture Synthesis Algorithms on Regular and Near-regular Textures - Robotics Institute Carnegie Mellon University

A Comparison Study of Four Texture Synthesis Algorithms on Regular and Near-regular Textures

Wen-Chieh Lin, James H. Hays, Chenyu Wu, Vivek Kwatra, and Yanxi Liu
Tech. Report, CMU-RI-TR-04-01, Robotics Institute, Carnegie Mellon University, 2004

Abstract

We compare the performance of four texture synthesis algorithms on synthesizing regular and near-regular textures in this report. Our results show that the near-regular texture synthesis remains to be a challenging problem. This is because a near-regular texture demonstrates both global regularity and local randomness in its texture pattern. It is difficult to preserve both properties in the synthetic textures. The comparison indicates that a specially-designed texture synthesis algorithm that respects the nature of near-regular textures can produce more faithfully synthesized textures than general purpose state of the art synthesis algorithms.

BibTeX

@techreport{Lin-2004-8846,
author = {Wen-Chieh Lin and James H. Hays and Chenyu Wu and Vivek Kwatra and Yanxi Liu},
title = {A Comparison Study of Four Texture Synthesis Algorithms on Regular and Near-regular Textures},
year = {2004},
month = {January},
institute = {Carnegie Mellon University},
address = {Pittsburgh, PA},
number = {CMU-RI-TR-04-01},
}