AIR-Nets : An Attention-Based Framework for Locally Conditioned Implicit Representations

Lade...
Vorschaubild
Dateien
Zu diesem Dokument gibt es keine Dateien.
Datum
2021
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
ArXiv-ID
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
2021 International Conference on 3D Vision, 3DV 2021 : , virtual conference ; 1-3 December 2021 : proceedings. Piscataway: IEEE, 2021, pp. 1054-1064. ISBN 978-1-66542-688-6. Available under: doi: 10.1109/3DV53792.2021.00113
Zusammenfassung

This paper introduces Attentive Implicit Representation Networks (AIR-Nets), a simple, but highly effective architecture for 3D reconstruction from point clouds. Since representing 3D shapes in a local and modular fashion increases generalization and reconstruction quality, AIR-Nets encode an input point cloud into a set of local latent vectors anchored in 3D space, which locally describe the object’s geometry, as well as a global latent description, enforcing global consistency. Our model is the first grid-free, encoder-based approach that locally describes an implicit function. The vector attention mechanism from [62] serves as main point cloud processing module, and allows for permutation invariance and translation equivariance. When queried with a 3D coordinate, our decoder gathers information from the global and nearby local latent vectors in order to predict an occupancy value. Experiments on the ShapeNet dataset [7] show that AIR-Nets significantly outperform previous state-of-the-art encoder-based, implicit shape learning methods and especially dominate in the sparse setting. Furthermore, our model generalizes well to the FAUST dataset [1] in a zero-shot setting. Finally, since AIR-Nets use a sparse latent representation and follow a simple operating scheme, the model offers several exiting avenues for future work. Our code is available at https: //github.com/SimonGiebenhain/AIR-Nets.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Implicit Functions, Local Shape Representation, 3D Reconstruction
Konferenz
International Conference on 3D Vision : 3DV 2021, 1. Dez. 2021 - 3. Dez. 2021, Online
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690GIEBENHAIN, Simon, Bastian GOLDLÜCKE, 2021. AIR-Nets : An Attention-Based Framework for Locally Conditioned Implicit Representations. International Conference on 3D Vision : 3DV 2021. Online, 1. Dez. 2021 - 3. Dez. 2021. In: 2021 International Conference on 3D Vision, 3DV 2021 : , virtual conference ; 1-3 December 2021 : proceedings. Piscataway: IEEE, 2021, pp. 1054-1064. ISBN 978-1-66542-688-6. Available under: doi: 10.1109/3DV53792.2021.00113
BibTex
@inproceedings{Giebenhain2021AIRNe-57559,
  year={2021},
  doi={10.1109/3DV53792.2021.00113},
  title={AIR-Nets : An Attention-Based Framework for Locally Conditioned Implicit Representations},
  isbn={978-1-66542-688-6},
  publisher={IEEE},
  address={Piscataway},
  booktitle={2021 International Conference on 3D Vision, 3DV 2021 : , virtual conference ; 1-3 December 2021 : proceedings},
  pages={1054--1064},
  author={Giebenhain, Simon and Goldlücke, Bastian}
}
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/123456789/57559">
    <dc:contributor>Giebenhain, Simon</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:issued>2021</dcterms:issued>
    <dc:language>eng</dc:language>
    <dcterms:title>AIR-Nets : An Attention-Based Framework for Locally Conditioned Implicit Representations</dcterms:title>
    <dcterms:abstract xml:lang="eng">This paper introduces Attentive Implicit Representation Networks (AIR-Nets), a simple, but highly effective architecture for 3D reconstruction from point clouds. Since representing 3D shapes in a local and modular fashion increases generalization and reconstruction quality, AIR-Nets encode an input point cloud into a set of local latent vectors anchored in 3D space, which locally describe the object’s geometry, as well as a global latent description, enforcing global consistency. Our model is the first grid-free, encoder-based approach that locally describes an implicit function. The vector attention mechanism from [62] serves as main point cloud processing module, and allows for permutation invariance and translation equivariance. When queried with a 3D coordinate, our decoder gathers information from the global and nearby local latent vectors in order to predict an occupancy value. Experiments on the ShapeNet dataset [7] show that AIR-Nets significantly outperform previous state-of-the-art encoder-based, implicit shape learning methods and especially dominate in the sparse setting. Furthermore, our model generalizes well to the FAUST dataset [1] in a zero-shot setting. Finally, since AIR-Nets use a sparse latent representation and follow a simple operating scheme, the model offers several exiting avenues for future work. Our code is available at https: //github.com/SimonGiebenhain/AIR-Nets.</dcterms:abstract>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Goldlücke, Bastian</dc:creator>
    <dc:contributor>Goldlücke, Bastian</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/57559"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-05-17T10:51:33Z</dc:date>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-05-17T10:51:33Z</dcterms:available>
    <dc:creator>Giebenhain, Simon</dc:creator>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
URL der Originalveröffentl.
Prüfdatum der URL
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Ja
Diese Publikation teilen