TreePartNet : neural decomposition of point clouds for 3D tree reconstruction

Liu, Yanchao; Guo, Jianwei; Benes, Bedrich; Deussen, Oliver; Zhang, Xiaopeng; Huang, Hui

TreePartNet : neural decomposition of point clouds for 3D tree reconstruction

Dateien

Liu_2-13rmq34uz5o9h2.pdfGröße: 2.83 MBDownloads: 1078

Datum

2021

Autor:innen

Liu, Yanchao

Guo, Jianwei

Benes, Bedrich

Deussen, Oliver

Zhang, Xiaopeng

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). 2021, 40(6), 232. ISSN 0730-0301. eISSN 1557-7368. Available under: doi: 10.1145/3478513.3480486

Zusammenfassung

We present TreePartNet, a neural network aimed at reconstructing tree geometry from point clouds obtained by scanning real trees. Our key idea is to learn a natural neural decomposition exploiting the assumption that a tree comprises locally cylindrical shapes. In particular, reconstruction is a two-step process. First, two networks are used to detect priors from the point clouds. One detects semantic branching points, and the other network is trained to learn a cylindrical representation of the branches. In the second step, we apply a neural merging module to reduce the cylindrical representation to a final set of generalized cylinders combined by branches. We demonstrate results of reconstructing realistic tree geometry for a variety of input models and with varying input point quality, e.g., noise, outliers, and incompleteness. We evaluate our approach extensively by using data from both synthetic and real trees and comparing it with alternative methods.

Fachgebiet (DDC)

004 Informatik

Zitieren

ISO 690

LIU, Yanchao, Jianwei GUO, Bedrich BENES, Oliver DEUSSEN, Xiaopeng ZHANG, Hui HUANG, 2021. TreePartNet : neural decomposition of point clouds for 3D tree reconstruction. In: ACM Transactions on Graphics. Association for Computing Machinery (ACM). 2021, 40(6), 232. ISSN 0730-0301. eISSN 1557-7368. Available under: doi: 10.1145/3478513.3480486

BibTex

@article{Liu2021TreeP-55977,
  year={2021},
  doi={10.1145/3478513.3480486},
  title={TreePartNet : neural decomposition of point clouds for 3D tree reconstruction},
  number={6},
  volume={40},
  issn={0730-0301},
  journal={ACM Transactions on Graphics},
  author={Liu, Yanchao and Guo, Jianwei and Benes, Bedrich and Deussen, Oliver and Zhang, Xiaopeng and Huang, Hui},
  note={Article Number: 232}
}

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/123456789/55977">
    <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">2021-12-22T08:07:58Z</dcterms:available>
    <dc:creator>Guo, Jianwei</dc:creator>
    <dc:creator>Deussen, Oliver</dc:creator>
    <dc:creator>Liu, Yanchao</dc:creator>
    <dc:creator>Zhang, Xiaopeng</dc:creator>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/55977/1/Liu_2-13rmq34uz5o9h2.pdf"/>
    <dcterms:issued>2021</dcterms:issued>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/55977/1/Liu_2-13rmq34uz5o9h2.pdf"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/55977"/>
    <dc:contributor>Zhang, Xiaopeng</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-12-22T08:07:58Z</dc:date>
    <dc:contributor>Huang, Hui</dc:contributor>
    <dc:contributor>Deussen, Oliver</dc:contributor>
    <dc:language>eng</dc:language>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:title>TreePartNet : neural decomposition of point clouds for 3D tree reconstruction</dcterms:title>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:rights>terms-of-use</dc:rights>
    <dc:creator>Huang, Hui</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:contributor>Guo, Jianwei</dc:contributor>
    <dc:contributor>Liu, Yanchao</dc:contributor>
    <dc:contributor>Benes, Bedrich</dc:contributor>
    <dcterms:abstract xml:lang="eng">We present TreePartNet, a neural network aimed at reconstructing tree geometry from point clouds obtained by scanning real trees. Our key idea is to learn a natural neural decomposition exploiting the assumption that a tree comprises locally cylindrical shapes. In particular, reconstruction is a two-step process. First, two networks are used to detect priors from the point clouds. One detects semantic branching points, and the other network is trained to learn a cylindrical representation of the branches. In the second step, we apply a neural merging module to reduce the cylindrical representation to a final set of generalized cylinders combined by branches. We demonstrate results of reconstructing realistic tree geometry for a variety of input models and with varying input point quality, e.g., noise, outliers, and incompleteness. We evaluate our approach extensively by using data from both synthetic and real trees and comparing it with alternative methods.</dcterms:abstract>
    <dc:creator>Benes, Bedrich</dc:creator>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja

Begutachtet

Ja