UM  > 科技學院  > 電腦及資訊科學系
An iterated randomized search algorithm for large-scale texture synthesis and manipulations
Chuanyan Hao1; Yadang Chen1; Wen Wu1; Enhua Wu1,2
2015-11-01
Source PublicationThe Visual Computer
ISSN017-789
Volume31Issue:11Pages:1447-1458
Abstract

In this paper, we introduce a novel iterated random search method for large-scale texture synthesis and manipulations. Previous researches on texture synthesis and manipulation have reached a great achievement both on quality and performance. However, the cost of the popular exhaustive search-based methods is still high especially for large-scale and complex synthesis scenes. Our algorithm contributes great improvements on performances about 2–50 times over the typical patch-based synthesis methods. Texture patterns have been well-known formalized as a Markov Random Field (MRF) whose two hypotheses, stationarity and locality, drive our bold guess that a random sampling may just catch a good match and allows us to propagate the natural coherence in the neighborhood. Meanwhile, the iteration constantly updates the bad guesses to make our algorithm converge fast with the results in the state of the art. We also provide a simple theoretical analysis to compare our iterated randomized search model and the classical synthesis algorithms. Besides, this simple method turns out to work well in various applications as well, such as texture transfer, image completion and video synthesis.

KeywordApproximate Match Patch Coherent Propagation Random Search Texture Synthesis Texture Transfer
DOI10.1007/s00371-014-1025-3
URLView the original
Indexed BySCI
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Software Engineering
WOS IDWOS:000362680600002
Fulltext Access
Citation statistics
Cited Times [WOS]:1   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Faculty of Science and Technology
Corresponding AuthorChuanyan Hao
Affiliation1.FST, University of Macau, Macao, China
2.State Key Lab of CS Institute of Software, Chinese Academy of Sciences, Beijing, China
First Author AffilicationUniversity of Macau
Corresponding Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Chuanyan Hao,Yadang Chen,Wen Wu,et al. An iterated randomized search algorithm for large-scale texture synthesis and manipulations[J]. The Visual Computer,2015,31(11):1447-1458.
APA Chuanyan Hao,Yadang Chen,Wen Wu,&Enhua Wu.(2015).An iterated randomized search algorithm for large-scale texture synthesis and manipulations.The Visual Computer,31(11),1447-1458.
MLA Chuanyan Hao,et al."An iterated randomized search algorithm for large-scale texture synthesis and manipulations".The Visual Computer 31.11(2015):1447-1458.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chuanyan Hao]'s Articles
[Yadang Chen]'s Articles
[Wen Wu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chuanyan Hao]'s Articles
[Yadang Chen]'s Articles
[Wen Wu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chuanyan Hao]'s Articles
[Yadang Chen]'s Articles
[Wen Wu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.