Data-Driven Synthesis of Cartoon Faces Using Different Styles

Zhang, Yong; Dong, Weiming; Ma, Chongyang; Mei, Xing; Li, Ke; Huang, Feiyue; Hu, Bao-Gang; Deussen, Oliver

Data-Driven Synthesis of Cartoon Faces Using Different Styles

Dateien

Zhang_0-373557.pdfGröße: 2.34 MBDownloads: 1046

Datum

2017

Autor:innen

Zhang, Yong

Dong, Weiming

Ma, Chongyang

Mei, Xing

Li, Ke

Huang, Feiyue

Hu, Bao-Gang

Deussen, Oliver

Open Access-Veröffentlichung

Open Access Green

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Zeitschriftenartikel

Publikationsstatus

Published

Erschienen in

IEEE Transactions on image processing. 2017, 26(1), pp. 464-478. ISSN 1057-7149. eISSN 1941-0042. Available under: doi: 10.1109/TIP.2016.2628581

Zusammenfassung

This paper presents a data-driven approach for automatically generating cartoon faces in different styles from a given portrait image. Our stylization pipeline consists of two steps: an offline analysis step to learn about how to select and compose facial components from the databases; a runtime synthesis step to generate the cartoon face by assembling parts from a database of stylized facial components. We propose an optimization framework that, for a given artistic style, simultaneously considers the desired image-cartoon relationships of the facial components and a proper adjustment of the image composition. We measure the similarity between facial components of the input image and our cartoon database via image feature matching, and introduce a probabilistic framework for modeling the relationships between cartoon facial components. We incorporate prior knowledge about image-cartoon relationships and the optimal composition of facial components extracted from a set of cartoon faces to maintain a natural, consistent, and attractive look of the results. We demonstrate generality and robustness of our approach by applying it to a variety of portrait images and compare our output with stylized results created by artists via a comprehensive user study

Fachgebiet (DDC)

004 Informatik

Schlagwörter

Cartoon face, face stylization, data-driven synthesis, component-based modeling

Zitieren

ISO 690

ZHANG, Yong, Weiming DONG, Chongyang MA, Xing MEI, Ke LI, Feiyue HUANG, Bao-Gang HU, Oliver DEUSSEN, 2017. Data-Driven Synthesis of Cartoon Faces Using Different Styles. In: IEEE Transactions on image processing. 2017, 26(1), pp. 464-478. ISSN 1057-7149. eISSN 1941-0042. Available under: doi: 10.1109/TIP.2016.2628581

BibTex

@article{Zhang2017DataD-36075,
  year={2017},
  doi={10.1109/TIP.2016.2628581},
  title={Data-Driven Synthesis of Cartoon Faces Using Different Styles},
  number={1},
  volume={26},
  issn={1057-7149},
  journal={IEEE Transactions on image processing},
  pages={464--478},
  author={Zhang, Yong and Dong, Weiming and Ma, Chongyang and Mei, Xing and Li, Ke and Huang, Feiyue and Hu, Bao-Gang and Deussen, Oliver}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36075">
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/36075"/>
    <dc:contributor>Deussen, Oliver</dc:contributor>
    <dc:contributor>Dong, Weiming</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2016-11-25T09:24:04Z</dcterms:available>
    <dc:contributor>Ma, Chongyang</dc:contributor>
    <dc:contributor>Hu, Bao-Gang</dc:contributor>
    <dc:creator>Ma, Chongyang</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2016-11-25T09:24:04Z</dc:date>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:title>Data-Driven Synthesis of Cartoon Faces Using Different Styles</dcterms:title>
    <dc:contributor>Li, Ke</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:contributor>Zhang, Yong</dc:contributor>
    <dc:creator>Huang, Feiyue</dc:creator>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:creator>Hu, Bao-Gang</dc:creator>
    <dcterms:abstract xml:lang="eng">This paper presents a data-driven approach for automatically generating cartoon faces in different styles from a given portrait image. Our stylization pipeline consists of two steps: an offline analysis step to learn about how to select and compose facial components from the databases; a runtime synthesis step to generate the cartoon face by assembling parts from a database of stylized facial components. We propose an optimization framework that, for a given artistic style, simultaneously considers the desired image-cartoon relationships of the facial components and a proper adjustment of the image composition. We measure the similarity between facial components of the input image and our cartoon database via image feature matching, and introduce a probabilistic framework for modeling the relationships between cartoon facial components. We incorporate prior knowledge about image-cartoon relationships and the optimal composition of facial components extracted from a set of cartoon faces to maintain a natural, consistent, and attractive look of the results. We demonstrate generality and robustness of our approach by applying it to a variety of portrait images and compare our output with stylized results created by artists via a comprehensive user study</dcterms:abstract>
    <dc:creator>Dong, Weiming</dc:creator>
    <dc:language>eng</dc:language>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Li, Ke</dc:creator>
    <dc:creator>Deussen, Oliver</dc:creator>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/36075/3/Zhang_0-373557.pdf"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Zhang, Yong</dc:creator>
    <dc:creator>Mei, Xing</dc:creator>
    <dc:contributor>Huang, Feiyue</dc:contributor>
    <dc:contributor>Mei, Xing</dc:contributor>
    <dcterms:issued>2017</dcterms:issued>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/36075/3/Zhang_0-373557.pdf"/>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja