Body talk : crowdshaping realistic 3D avatars with words
Dateien
Datum
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
DOI (zitierfähiger Link)
Internationale Patentnummer
Link zur Lizenz
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Sammlungen
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
Realistic, metrically accurate, 3D human avatars are useful for games, shopping, virtual reality, and health applications. Such avatars are not in wide use because solutions for creating them from high-end scanners, low-cost range cameras, and tailoring measurements all have limitations. Here we propose a simple solution and show that it is surprisingly accurate. We use crowdsourcing to generate attribute ratings of 3D body shapes corresponding to standard linguistic descriptions of 3D shape. We then learn a linear function relating these ratings to 3D human shape parameters. Given an image of a new body, we again turn to the crowd for ratings of the body shape. The collection of linguistic ratings of a photograph provides remarkably strong constraints on the metric 3D shape. We call the process crowdshaping and show that our Body Talk system produces shapes that are perceptually indistinguishable from bodies created from high-resolution scans and that the metric accuracy is sufficient for many tasks. This makes body "scanning" practical without a scanner, opening up new applications including database search, visualization, and extracting avatars from books.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
STREUBER, Stephan, M. Alejandra QUIROS-RAMIREZ, Matthew Q. HILL, Carina A. HAHN, Silvia ZUFFI, Alice O'TOOLE, Michael J. BLACK, 2016. Body talk : crowdshaping realistic 3D avatars with words. In: ACM Transactions on Graphics. 2016, 35(4), 54. ISSN 0730-0301. eISSN 1557-7368. Available under: doi: 10.1145/2897824.2925981BibTex
@article{Streuber2016-07-11crowd-43403, year={2016}, doi={10.1145/2897824.2925981}, title={Body talk : crowdshaping realistic 3D avatars with words}, number={4}, volume={35}, issn={0730-0301}, journal={ACM Transactions on Graphics}, author={Streuber, Stephan and Quiros-Ramirez, M. Alejandra and Hill, Matthew Q. and Hahn, Carina A. and Zuffi, Silvia and O'Toole, Alice and Black, Michael J.}, note={Article Number: 54} }
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/123456789/43403"> <dcterms:title>Body talk : crowdshaping realistic 3D avatars with words</dcterms:title> <dc:creator>Zuffi, Silvia</dc:creator> <dc:creator>Quiros-Ramirez, M. Alejandra</dc:creator> <dc:contributor>Zuffi, Silvia</dc:contributor> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-10-01T08:30:34Z</dc:date> <dcterms:issued>2016-07-11</dcterms:issued> <dc:creator>Hahn, Carina A.</dc:creator> <dc:contributor>Hill, Matthew Q.</dc:contributor> <dc:creator>Hill, Matthew Q.</dc:creator> <dc:language>eng</dc:language> <dc:creator>Streuber, Stephan</dc:creator> <dc:creator>Black, Michael J.</dc:creator> <dc:contributor>O'Toole, Alice</dc:contributor> <dc:contributor>Hahn, Carina A.</dc:contributor> <dc:rights>Attribution-NonCommercial-ShareAlike 4.0 International</dc:rights> <dc:contributor>Quiros-Ramirez, M. Alejandra</dc:contributor> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/43403"/> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:contributor>Streuber, Stephan</dc:contributor> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/43403/1/Streuber_2-1q83u4bskzuzx6.pdf"/> <dcterms:abstract xml:lang="eng">Realistic, metrically accurate, 3D human avatars are useful for games, shopping, virtual reality, and health applications. Such avatars are not in wide use because solutions for creating them from high-end scanners, low-cost range cameras, and tailoring measurements all have limitations. Here we propose a simple solution and show that it is surprisingly accurate. We use crowdsourcing to generate attribute ratings of 3D body shapes corresponding to standard linguistic descriptions of 3D shape. We then learn a linear function relating these ratings to 3D human shape parameters. Given an image of a new body, we again turn to the crowd for ratings of the body shape. The collection of linguistic ratings of a photograph provides remarkably strong constraints on the metric 3D shape. We call the process crowdshaping and show that our Body Talk system produces shapes that are perceptually indistinguishable from bodies created from high-resolution scans and that the metric accuracy is sufficient for many tasks. This makes body "scanning" practical without a scanner, opening up new applications including database search, visualization, and extracting avatars from books.</dcterms:abstract> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-10-01T08:30:34Z</dcterms:available> <dc:contributor>Black, Michael J.</dc:contributor> <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by-nc-sa/4.0/"/> <dc:creator>O'Toole, Alice</dc:creator> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/43403/1/Streuber_2-1q83u4bskzuzx6.pdf"/> </rdf:Description> </rdf:RDF>