Inverse Procedural Modeling of Branching Structures by Inferring L-Systems

Guo, Jianwei; Jiang, Haiyong; Benes, Bedrich; Deussen, Oliver; Lischinski, Dani; Huang, Hui

Inverse Procedural Modeling of Branching Structures by Inferring L-Systems

Dateien

Guo_2-1bwz7hxf8eixx3.pdfGröße: 2.96 MBDownloads: 1146

Datum

2020

Autor:innen

Guo, Jianwei

Jiang, Haiyong

Benes, Bedrich

Deussen, Oliver

Lischinski, Dani

Huang, Hui

Open Access-Veröffentlichung

Open Access Green

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Zeitschriftenartikel

Publikationsstatus

Published

Erschienen in

ACM Transactions on Graphics. Association for Computing Machinery (ACM). 2020, 39(5), pp. 1-13. ISSN 0730-0301. eISSN 1557-7368. Available under: doi: 10.1145/3394105

Zusammenfassung

We introduce an inverse procedural modeling approach that learns L-system representations of pixel images with branching structures. Our fully automatic model generates a compact set of textual rewriting rules that describe the input. We use deep learning to discover atomic structures such as line segments or branchings. Orientation and scaling of these structures is determined and the detected structures are combined into a tree. The initial representation is analyzed, and repeating parts are encoded into a small grammar by using greedy optimization while the user can control the size of the detected rules. The output is an L-system that represents the input image as a simple text and a set of terminal symbols. We apply our approach to a variety of examples, demonstrate its robustness against noise and blur, and we show that it can detect user sketches and complex input structures.

Fachgebiet (DDC)

004 Informatik

Zitieren

ISO 690

GUO, Jianwei, Haiyong JIANG, Bedrich BENES, Oliver DEUSSEN, Dani LISCHINSKI, Hui HUANG, 2020. Inverse Procedural Modeling of Branching Structures by Inferring L-Systems. In: ACM Transactions on Graphics. Association for Computing Machinery (ACM). 2020, 39(5), pp. 1-13. ISSN 0730-0301. eISSN 1557-7368. Available under: doi: 10.1145/3394105

BibTex

@article{Guo2020-06-15Inver-49640,
  year={2020},
  doi={10.1145/3394105},
  title={Inverse Procedural Modeling of Branching Structures by Inferring L-Systems},
  number={5},
  volume={39},
  issn={0730-0301},
  journal={ACM Transactions on Graphics},
  pages={1--13},
  author={Guo, Jianwei and Jiang, Haiyong and Benes, Bedrich and Deussen, Oliver and Lischinski, Dani and Huang, Hui}
}

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/123456789/49640">
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:contributor>Jiang, Haiyong</dc:contributor>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:issued>2020-06-15</dcterms:issued>
    <dc:creator>Guo, Jianwei</dc:creator>
    <dc:creator>Lischinski, Dani</dc:creator>
    <dc:creator>Deussen, Oliver</dc:creator>
    <dc:creator>Jiang, Haiyong</dc:creator>
    <dc:contributor>Guo, Jianwei</dc:contributor>
    <dc:contributor>Deussen, Oliver</dc:contributor>
    <dc:language>eng</dc:language>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/49640"/>
    <dcterms:title>Inverse Procedural Modeling of Branching Structures by Inferring L-Systems</dcterms:title>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/49640/1/Guo_2-1bwz7hxf8eixx3.pdf"/>
    <dc:contributor>Benes, Bedrich</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-05-26T06:57:06Z</dc:date>
    <dc:creator>Huang, Hui</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-05-26T06:57:06Z</dcterms:available>
    <dc:contributor>Huang, Hui</dc:contributor>
    <dcterms:abstract xml:lang="eng">We introduce an inverse procedural modeling approach that learns L-system representations of pixel images with branching structures. Our fully automatic model generates a compact set of textual rewriting rules that describe the input. We use deep learning to discover atomic structures such as line segments or branchings. Orientation and scaling of these structures is determined and the detected structures are combined into a tree. The initial representation is analyzed, and repeating parts are encoded into a small grammar by using greedy optimization while the user can control the size of the detected rules. The output is an L-system that represents the input image as a simple text and a set of terminal symbols. We apply our approach to a variety of examples, demonstrate its robustness against noise and blur, and we show that it can detect user sketches and complex input structures.</dcterms:abstract>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/49640/1/Guo_2-1bwz7hxf8eixx3.pdf"/>
    <dc:rights>terms-of-use</dc:rights>
    <dc:creator>Benes, Bedrich</dc:creator>
    <dc:contributor>Lischinski, Dani</dc:contributor>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja

Begutachtet

Ja