Quantitative Evaluation of Near Regular Texture Synthesis Algorithms

Authors:
Wen-Chieh Lin;James Hays;Chenyu Wu;Yanxi Liu;Vivek Kwatra
Affiliations:
National Chiao-Tung University;Carnegie Mellon University;Carnegie Mellon University;Carnegie Mellon University;University of North Carolina at Chapel Hill
Venue:
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Year:
2006

Citing 0
Cited 7

Periodicity estimation of Dynamic Textures

International Journal of Information and Communication Technology
Towards ground truth in geometric textures

Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Non-Photorealistic Animation and Rendering
Homogeneity cues for texel size estimation of periodic and near-periodic textures

MCPR'11 Proceedings of the Third Mexican conference on Pattern recognition
Automatic extraction of texture-periodicity using superposition of distance matching functions and their forward differences

Pattern Recognition Letters
Automatic restoration of corrupted regions in images using object width transform

Proceedings of the 6th International Conference on Ubiquitous Information Management and Communication
Fast texel size estimation in visual texture using homogeneity cues

Pattern Recognition Letters
Towards effective evaluation of geometric texture synthesis algorithms

Proceedings of the Symposium on Non-Photorealistic Animation and Rendering

Quantified Score

Hi-index	0.00

Visualization

Abstract

Near regular textures are pervasive in man-made and natural world. Their global regularity and local randomness pose new difficulties to the state of the art texture analysis and synthesis algorithms. We carry out a systematic comparison study on the performance of four texture synthesis algorithms on near-regular textures. Our results confirm that faithful near-regular texture synthesis remains a challenging problem for the state of the art general purpose texture synthesis algorithms. In addition, we provide comparison of human perception with computer evaluations on the quality of the texture synthesis results.