Data-driven face cartoon stylization

Cite This

Files in this item

Checksum: MD5:f41291534648369bddaa54884aa28138

ZHANG, Yong, Weiming DONG, Oliver DEUSSEN, Feiyue HUANG, Ke LI, Bao-Gang HU, 2014. Data-driven face cartoon stylization. SIGGRAPH Asia 2014. Shenzhen, China, Dec 3, 2014 - Dec 6, 2014. In: SIGGRAPH Asia 2014 Technical Briefs. New York:ACM, 14. ISBN 978-1-4503-2895-1. Available under: doi: 10.1145/2669024.2669028

@inproceedings{Zhang2014Datad-30527, title={Data-driven face cartoon stylization}, year={2014}, doi={10.1145/2669024.2669028}, isbn={978-1-4503-2895-1}, address={New York}, publisher={ACM}, booktitle={SIGGRAPH Asia 2014 Technical Briefs}, author={Zhang, Yong and Dong, Weiming and Deussen, Oliver and Huang, Feiyue and Li, Ke and Hu, Bao-Gang}, note={Article Number: 14} }

<rdf:RDF xmlns:dcterms="" xmlns:dc="" xmlns:rdf="" xmlns:bibo="" xmlns:dspace="" xmlns:foaf="" xmlns:void="" xmlns:xsd="" > <rdf:Description rdf:about=""> <dcterms:rights rdf:resource=""/> <dc:creator>Dong, Weiming</dc:creator> <dspace:hasBitstream rdf:resource=""/> <dc:contributor>Dong, Weiming</dc:contributor> <dc:contributor>Li, Ke</dc:contributor> <dc:contributor>Deussen, Oliver</dc:contributor> <dspace:isPartOfCollection rdf:resource=""/> <dcterms:hasPart rdf:resource=""/> <dc:contributor>Huang, Feiyue</dc:contributor> <dc:date rdf:datatype="">2015-03-25T06:25:24Z</dc:date> <dc:creator>Li, Ke</dc:creator> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:title>Data-driven face cartoon stylization</dcterms:title> <dc:contributor>Zhang, Yong</dc:contributor> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dcterms:abstract xml:lang="eng">This paper presents a data-driven framework for generating cartoon-like facial representations from a given portrait image. We solve our problem by an optimization that simultaneously considers a desired artistic style, image-cartoon relationships of facial components as well as automatic adjustment of the image composition. The stylization operation consists of two steps: a face parsing step to localize and extract facial components from the input image; a cartoon generation step to cartoonize the face according to the extracted information. The components of the cartoon are assembled from a database of stylized facial components. Quantifying the similarity between facial components of input and cartoon is done by image feature matching. We incorporate prior knowledge about photo-cartoon relationships and the optimal composition of cartoon facial components extracted from a set of cartoon faces to maintain a natural and attractive look of the results.</dcterms:abstract> <dc:rights>terms-of-use</dc:rights> <dc:creator>Deussen, Oliver</dc:creator> <dcterms:isPartOf rdf:resource=""/> <dc:creator>Zhang, Yong</dc:creator> <dcterms:issued>2014</dcterms:issued> <bibo:uri rdf:resource=""/> <dc:creator>Hu, Bao-Gang</dc:creator> <dc:creator>Huang, Feiyue</dc:creator> <dc:language>eng</dc:language> <dc:contributor>Hu, Bao-Gang</dc:contributor> <dcterms:available rdf:datatype="">2015-03-25T06:25:24Z</dcterms:available> </rdf:Description> </rdf:RDF>

Downloads since Mar 25, 2015 (Information about access statistics)

Zhang_0-277918.pdf 1283

This item appears in the following Collection(s)

Search KOPS


My Account