Quantitative evaluation of near regular texture synthesis algorithms

Wen Chieh Lin, James Hays, Chenyu Wu, Vivek Kwatra, Yanxi Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

41 Citations (Scopus)

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.

Original languageEnglish (US)
Title of host publicationProceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Pages427-434
Number of pages8
DOIs
StatePublished - Dec 22 2006
Event2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 - New York, NY, United States
Duration: Jun 17 2006Jun 22 2006

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume1
ISSN (Print)1063-6919

Other

Other2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
CountryUnited States
CityNew York, NY
Period6/17/066/22/06

Fingerprint

Textures

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Lin, W. C., Hays, J., Wu, C., Kwatra, V., & Liu, Y. (2006). Quantitative evaluation of near regular texture synthesis algorithms. In Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 (pp. 427-434). [1640789] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 1). https://doi.org/10.1109/CVPR.2006.233
Lin, Wen Chieh ; Hays, James ; Wu, Chenyu ; Kwatra, Vivek ; Liu, Yanxi. / Quantitative evaluation of near regular texture synthesis algorithms. Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. pp. 427-434 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{3ec23c00472c4a488c8ea868b502976e,
title = "Quantitative evaluation of near regular texture synthesis algorithms",
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.",
author = "Lin, {Wen Chieh} and James Hays and Chenyu Wu and Vivek Kwatra and Yanxi Liu",
year = "2006",
month = "12",
day = "22",
doi = "10.1109/CVPR.2006.233",
language = "English (US)",
isbn = "0769525970",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
pages = "427--434",
booktitle = "Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006",

}

Lin, WC, Hays, J, Wu, C, Kwatra, V & Liu, Y 2006, Quantitative evaluation of near regular texture synthesis algorithms. in Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006., 1640789, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 427-434, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, New York, NY, United States, 6/17/06. https://doi.org/10.1109/CVPR.2006.233

Quantitative evaluation of near regular texture synthesis algorithms. / Lin, Wen Chieh; Hays, James; Wu, Chenyu; Kwatra, Vivek; Liu, Yanxi.

Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. p. 427-434 1640789 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Quantitative evaluation of near regular texture synthesis algorithms

AU - Lin, Wen Chieh

AU - Hays, James

AU - Wu, Chenyu

AU - Kwatra, Vivek

AU - Liu, Yanxi

PY - 2006/12/22

Y1 - 2006/12/22

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=33845583381&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845583381&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2006.233

DO - 10.1109/CVPR.2006.233

M3 - Conference contribution

AN - SCOPUS:33845583381

SN - 0769525970

SN - 9780769525976

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 427

EP - 434

BT - Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006

ER -

Lin WC, Hays J, Wu C, Kwatra V, Liu Y. Quantitative evaluation of near regular texture synthesis algorithms. In Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. p. 427-434. 1640789. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2006.233