Feature-aware natural texture synthesis

Handle URI:
http://hdl.handle.net/10754/566111
Title:
Feature-aware natural texture synthesis
Authors:
Wu, Fuzhang; Dong, Weiming; Kong, Yan; Mei, Xing; Yan, Dongming ( 0000-0003-2209-2404 ) ; Zhang, Xiaopeng; Paul, Jean Claude
Abstract:
This 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.
KAUST Department:
Visual Computing Center (VCC)
Publisher:
Springer Science + Business Media
Journal:
The Visual Computer
Issue Date:
4-Dec-2014
DOI:
10.1007/s00371-014-1054-y
Type:
Article
ISSN:
01782789
Appears in Collections:
Articles; Visual Computing Center (VCC)

Full metadata record

DC FieldValue Language
dc.contributor.authorWu, Fuzhangen
dc.contributor.authorDong, Weimingen
dc.contributor.authorKong, Yanen
dc.contributor.authorMei, Xingen
dc.contributor.authorYan, Dongmingen
dc.contributor.authorZhang, Xiaopengen
dc.contributor.authorPaul, Jean Claudeen
dc.date.accessioned2015-08-12T09:28:43Zen
dc.date.available2015-08-12T09:28:43Zen
dc.date.issued2014-12-04en
dc.identifier.issn01782789en
dc.identifier.doi10.1007/s00371-014-1054-yen
dc.identifier.urihttp://hdl.handle.net/10754/566111en
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.en
dc.publisherSpringer Science + Business Mediaen
dc.subjectComposite textureen
dc.subjectFeature-aware synthesisen
dc.subjectTexture feature analysisen
dc.subjectTexture synthesisen
dc.titleFeature-aware natural texture synthesisen
dc.typeArticleen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journalThe Visual Computeren
dc.contributor.institutionLIAMA-NLPR, Institute of Automation, Chinese Academy of SciencesBeijing, Chinaen
dc.contributor.institutionProject CAD, INRIAParis, Franceen
kaust.authorYan, Dongmingen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.