Show simple item record

dc.contributor.authorWu, Fuzhang
dc.contributor.authorDong, Weiming
dc.contributor.authorKong, Yan
dc.contributor.authorMei, Xing
dc.contributor.authorYan, Dongming
dc.contributor.authorZhang, Xiaopeng
dc.contributor.authorPaul, Jean Claude
dc.date.accessioned2015-08-12T09:28:43Z
dc.date.available2015-08-12T09:28:43Z
dc.date.issued2014-12-04
dc.identifier.issn01782789
dc.identifier.doi10.1007/s00371-014-1054-y
dc.identifier.urihttp://hdl.handle.net/10754/566111
dc.description.abstractThis article presents a framework for natural texture synthesis and processing. This framework is motivated by the observation that given examples captured in natural scene, texture synthesis addresses a critical problem, namely, that synthesis quality can be affected adversely if the texture elements in an example display spatially varied patterns, such as perspective distortion, the composition of different sub-textures, and variations in global color pattern as a result of complex illumination. This issue is common in natural textures and is a fundamental challenge for previously developed methods. Thus, we address it from a feature point of view and propose a feature-aware approach to synthesize natural textures. The synthesis process is guided by a feature map that represents the visual characteristics of the input texture. Moreover, we present a novel adaptive initialization algorithm that can effectively avoid the repeat and verbatim copying artifacts. Our approach improves texture synthesis in many images that cannot be handled effectively with traditional technologies.
dc.publisherSpringer Science + Business Media
dc.subjectComposite texture
dc.subjectFeature-aware synthesis
dc.subjectTexture feature analysis
dc.subjectTexture synthesis
dc.titleFeature-aware natural texture synthesis
dc.typeArticle
dc.contributor.departmentVisual Computing Center (VCC)
dc.identifier.journalThe Visual Computer
dc.contributor.institutionLIAMA-NLPR, Institute of Automation, Chinese Academy of SciencesBeijing, China
dc.contributor.institutionProject CAD, INRIAParis, France
kaust.personYan, Dongming


This item appears in the following Collection(s)

Show simple item record