Publikation: Neural Image abstraction using long smoothing B-splines
Lade...
Dateien
Datum
2025
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
Deutsche Forschungsgemeinschaft (DFG): 508324734
Projekt
Open Access-Veröffentlichung
Open Access Hybrid
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Zeitschriftenartikel
Publikationsstatus
Published
Erschienen in
ACM Transactions on Graphics. Association for Computing Machinery (ACM). 2025, 44(6), 225. ISSN 0730-0301. eISSN 1557-7368. Verfügbar unter: doi: 10.1145/3763345
Zusammenfassung
We integrate smoothing B-splines into a standard differentiable vector graphics (DiffVG) pipeline through linear mapping, and show how this can be used to generate smooth and arbitrarily long paths within image-based deep learning systems. We take advantage of derivative-based smoothing costs for parametric control of fidelity vs. simplicity tradeoffs, while also enabling stylization control in geometric and image spaces. The proposed pipeline is compatible with recent vector graphics generation and vectorization methods. We demonstrate the versatility of our approach with four applications aimed at the generation of stylized vector graphics: stylized space-filling path generation, stroke-based image abstraction, closed-area image abstraction, and stylized text generation.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690
BERIO, Daniel, Michael STROH, Sylvain CALINON, Frederic FOL LEYMARIE, Oliver DEUSSEN, Ariel SHAMIR, 2025. Neural Image abstraction using long smoothing B-splines. In: ACM Transactions on Graphics. Association for Computing Machinery (ACM). 2025, 44(6), 225. ISSN 0730-0301. eISSN 1557-7368. Verfügbar unter: doi: 10.1145/3763345BibTex
@article{Berio2025-12Neura-75679,
title={Neural Image abstraction using long smoothing B-splines},
year={2025},
doi={10.1145/3763345},
number={6},
volume={44},
issn={0730-0301},
journal={ACM Transactions on Graphics},
author={Berio, Daniel and Stroh, Michael and Calinon, Sylvain and Fol Leymarie, Frederic and Deussen, Oliver and Shamir, Ariel},
note={Article Number: 225}
}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/123456789/75679">
<dc:contributor>Calinon, Sylvain</dc:contributor>
<dcterms:abstract>We integrate smoothing B-splines into a standard differentiable vector graphics (DiffVG) pipeline through linear mapping, and show how this can be used to generate smooth and arbitrarily long paths within image-based deep learning systems. We take advantage of derivative-based smoothing costs for parametric control of fidelity vs. simplicity tradeoffs, while also enabling stylization control in geometric and image spaces. The proposed pipeline is compatible with recent vector graphics generation and vectorization methods. We demonstrate the versatility of our approach with four applications aimed at the generation of stylized vector graphics: stylized space-filling path generation, stroke-based image abstraction, closed-area image abstraction, and stylized text generation.</dcterms:abstract>
<dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2026-01-14T08:15:14Z</dcterms:available>
<dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:contributor>Berio, Daniel</dc:contributor>
<void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
<dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
<dc:language>eng</dc:language>
<dc:creator>Fol Leymarie, Frederic</dc:creator>
<dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2026-01-14T08:15:14Z</dc:date>
<dc:contributor>Shamir, Ariel</dc:contributor>
<dc:creator>Calinon, Sylvain</dc:creator>
<bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/75679"/>
<dc:contributor>Stroh, Michael</dc:contributor>
<dc:creator>Stroh, Michael</dc:creator>
<dc:creator>Deussen, Oliver</dc:creator>
<dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/75679/1/Berio_2-1j9fj994zzjod9.pdf"/>
<dcterms:issued>2025-12</dcterms:issued>
<dc:rights>terms-of-use</dc:rights>
<dc:contributor>Deussen, Oliver</dc:contributor>
<dc:contributor>Fol Leymarie, Frederic</dc:contributor>
<dcterms:title>Neural Image abstraction using long smoothing B-splines</dcterms:title>
<dc:creator>Berio, Daniel</dc:creator>
<dc:creator>Shamir, Ariel</dc:creator>
<dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/75679/1/Berio_2-1j9fj994zzjod9.pdf"/>
<foaf:homepage rdf:resource="http://localhost:8080/"/>
</rdf:Description>
</rdf:RDF>Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Ja
