An iterated randomized search algorithm for large-scale texture synthesis and manipulations

ISCAS OpenIR

	An iterated randomized search algorithm for large-scale texture synthesis and manipulations
	Hao, CY; Chen, YD; Wu, W; Wu, EH
	2015
发表期刊	VISUAL COMPUTER
ISSN	0178-2789
卷号	31 期号:11 页码:1447-1458
摘要	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.; 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.
收录类别	SCI
关键词	Texture Synthesis Coherent Propagation Random Search Texture Transfer Approximate Match Patch
部门归属	Univ Macau, FST, Macau, Peoples R China. Chinese Acad Sci, Inst Software, State Key Lab CS, Beijing, Peoples R China.
语种	英语
WOS记录号	WOS:000362680600002
引用统计
内容类型	期刊论文
URI标识	http://ir.iscas.ac.cn/handle/311060/17432
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Hao, CY,Chen, YD,Wu, W,et al. An iterated randomized search algorithm for large-scale texture synthesis and manipulations[J]. VISUAL COMPUTER,2015,31(11):1447-1458.
APA	Hao, CY,Chen, YD,Wu, W,&Wu, EH.(2015).An iterated randomized search algorithm for large-scale texture synthesis and manipulations.VISUAL COMPUTER,31(11),1447-1458.
MLA	Hao, CY,et al."An iterated randomized search algorithm for large-scale texture synthesis and manipulations".VISUAL COMPUTER 31.11(2015):1447-1458.