real time edit propagation by efficient sampling

ISCAS OpenIR

	real time edit propagation by efficient sampling
	Bie Xiaohui; Huang Haoda; Wang Wencheng
	2011
发表期刊	COMPUTER GRAPHICS FORUM
ISSN	0167-7055
卷号	30 期号:7 页码:2041-2048
摘要	It is popular to edit the appearance of images using strokes, owing to their ease of use and convenience of conveying the user's intention. However, propagating the user inputs to the rest of the images requires solving an enormous optimization problem, which is very time consuming, thus preventing its practical use. In this paper, a two-step edit propagation scheme is proposed, first to solve edits on clusters of similar pixels and then to interpolate individual pixel edits from cluster edits. The key in our scheme is that we use efficient stroke sampling to compute the affinity between image pixels and strokes. Based on this, our clustering does not need to be stroke-adaptive and thus the number of clusters is greatly reduced, resulting in a significant speedup. The proposed method has been tested on various images, and the results show that it is more than one order of magnitude faster than existing methods, while still achieving precise results compared with the ground truth. Moreover, its efficiency is not sensitive to the number of strokes, making it suitable for performing dense edits in practice.; It is popular to edit the appearance of images using strokes, owing to their ease of use and convenience of conveying the user's intention. However, propagating the user inputs to the rest of the images requires solving an enormous optimization problem, which is very time consuming, thus preventing its practical use. In this paper, a two-step edit propagation scheme is proposed, first to solve edits on clusters of similar pixels and then to interpolate individual pixel edits from cluster edits. The key in our scheme is that we use efficient stroke sampling to compute the affinity between image pixels and strokes. Based on this, our clustering does not need to be stroke-adaptive and thus the number of clusters is greatly reduced, resulting in a significant speedup. The proposed method has been tested on various images, and the results show that it is more than one order of magnitude faster than existing methods, while still achieving precise results compared with the ground truth. Moreover, its efficiency is not sensitive to the number of strokes, making it suitable for performing dense edits in practice.
收录类别	SCI
部门归属	Bie Xiaohui; Wang Wencheng Chinese Acad Sci Inst Software State Key Lab Comp Sci Beijing 100864 Peoples R China. Bie Xiaohui Chinese Acad Sci Grad Univ Beijing 100864 Peoples R China.
学科领域	Computer Science
资助者	NSFC60773026, 60873182, 60833007
语种	英语
WOS记录号	WOS:000296915400019
引用统计
内容类型	期刊论文
URI标识	http://ir.iscas.ac.cn/handle/311060/16074
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Bie Xiaohui,Huang Haoda,Wang Wencheng. real time edit propagation by efficient sampling[J]. COMPUTER GRAPHICS FORUM,2011,30(7):2041-2048.
APA	Bie Xiaohui,Huang Haoda,&Wang Wencheng.(2011).real time edit propagation by efficient sampling.COMPUTER GRAPHICS FORUM,30(7),2041-2048.
MLA	Bie Xiaohui,et al."real time edit propagation by efficient sampling".COMPUTER GRAPHICS FORUM 30.7(2011):2041-2048.