Intent-aware image cloning

ISCAS OpenIR

	Intent-aware image cloning
	Bie, Xiaohui; Wang, Wencheng; Sun, Hanqiu; Huang, Haoda; Zhang, Minying
	2013
发表期刊	VISUAL COMPUTER
ISSN	0178-2789
卷号	29 期号:6-8 页码:599-608
摘要	Currently, gradient domain methods are popular for producing seamless cloning of a source image patch into a target image. However, structure conflicts between the source image patch and the target image may generate artifacts, preventing the general practices. In this paper, we tackle the challenge by incorporating the users' intent in outlining the source patch, where the boundary drawn generally has different appearances from the objects of interest. We first reveal that artifacts exist in the over-included region, the region outside the objects of interest in the source patch. Then we use the diversity from the boundary to approximately distinguish the objects from the over-included region, and design a new algorithm to make the target image adaptively take effects in blending. So the structure conflicts can be efficiently suppressed to remove the artifacts around the objects of interest in the composite result. Moreover, we develop an interpolation measure to composite the final image rather than solving a Poisson equation, and speed up the interpolation by treating pixels in clusters and using hierarchical sampling techniques. Our method is simple to use for instant and high-quality image cloning, in which users only need to outline a region of interested objects to process. Our experimental results have demonstrated the effectiveness of our cloning method.; Currently, gradient domain methods are popular for producing seamless cloning of a source image patch into a target image. However, structure conflicts between the source image patch and the target image may generate artifacts, preventing the general practices. In this paper, we tackle the challenge by incorporating the users' intent in outlining the source patch, where the boundary drawn generally has different appearances from the objects of interest. We first reveal that artifacts exist in the over-included region, the region outside the objects of interest in the source patch. Then we use the diversity from the boundary to approximately distinguish the objects from the over-included region, and design a new algorithm to make the target image adaptively take effects in blending. So the structure conflicts can be efficiently suppressed to remove the artifacts around the objects of interest in the composite result. Moreover, we develop an interpolation measure to composite the final image rather than solving a Poisson equation, and speed up the interpolation by treating pixels in clusters and using hierarchical sampling techniques. Our method is simple to use for instant and high-quality image cloning, in which users only need to outline a region of interested objects to process. Our experimental results have demonstrated the effectiveness of our cloning method.
收录类别	SCI
关键词	Intent Representation Image Cloning Image Composition
部门归属	[Bie, Xiaohui; Wang, Wencheng; Zhang, Minying] Chinese Acad Sci, Inst Software, State Key Lab Comp Sci, Beijing 100190, Peoples R China. [Sun, Hanqiu] Chinese Univ Hong Kong, Dept Comp Sci & Engn, Shatin, Hong Kong, Peoples R China. [Huang, Haoda] Google Inc, Mountain View, CA 94043 USA. [Bie, Xiaohui; Zhang, Minying] Univ Chinese Acad Sci, Beijing, Peoples R China.
语种	英语
WOS记录号	WOS:000319478400014
引用统计
内容类型	期刊论文
URI标识	http://ir.iscas.ac.cn/handle/311060/16930
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Bie, Xiaohui,Wang, Wencheng,Sun, Hanqiu,et al. Intent-aware image cloning[J]. VISUAL COMPUTER,2013,29(6-8):599-608.
APA	Bie, Xiaohui,Wang, Wencheng,Sun, Hanqiu,Huang, Haoda,&Zhang, Minying.(2013).Intent-aware image cloning.VISUAL COMPUTER,29(6-8),599-608.
MLA	Bie, Xiaohui,et al."Intent-aware image cloning".VISUAL COMPUTER 29.6-8(2013):599-608.