ACM SIGGRAPH 2004 Papers 2004
DOI: 10.1145/1186562.1015730
|View full text |Cite
|
Sign up to set email alerts
|

Feature matching and deformation for texture synthesis

Abstract: One significant problem in patch-based texture synthesis is the presence of broken features at the boundary of adjacent patches. The reason is that optimization schemes for patch merging may fail when neighborhood search cannot find satisfactory candidates in the sample texture because of an inaccurate similarity measure. In this paper, we consider both curvilinear features and their deformation. We develop a novel algorithm to perform feature matching and alignment by measuring structural similarity. Our tech… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
43
0

Year Published

2006
2006
2009
2009

Publication Types

Select...
3
3
1

Relationship

0
7

Authors

Journals

citations
Cited by 67 publications
(43 citation statements)
references
References 15 publications
0
43
0
Order By: Relevance
“…Recently, feature-matching methods in texture synthesis are proposed in [13], [37]. In [37], binary feature maps are first produced by using a two-pass Canny edge filter.…”
Section: Structure Deformationmentioning
confidence: 99%
See 3 more Smart Citations
“…Recently, feature-matching methods in texture synthesis are proposed in [13], [37]. In [37], binary feature maps are first produced by using a two-pass Canny edge filter.…”
Section: Structure Deformationmentioning
confidence: 99%
“…In [37], binary feature maps are first produced by using a two-pass Canny edge filter. Then, a 2D feature-matching process is applied.…”
Section: Structure Deformationmentioning
confidence: 99%
See 2 more Smart Citations
“…Nowadays neighborhood-based methods are popularly used in texture synthesis, including point-based techniques [19,4,1] and patch-based techniques [3,9,20,12,8]. Hybrid texture synthesis method has also already been developed [13].…”
Section: Introductionmentioning
confidence: 99%