GenDR : A Generalized Differentiable Renderer

No Thumbnail Available
Files
There are no files associated with this item.
Date
2022
Editors
Contact
Journal ISSN
Electronic ISSN
ISBN
Bibliographical data
Publisher
Series
URI (citable link)
ArXiv-ID
International patent number
Link to the license
oops
EU project number
Project
Open Access publication
Restricted until
Title in another language
Research Projects
Organizational Units
Journal Issue
Publication type
Contribution to a conference collection
Publication status
Published
Published in
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, proceedings / Chellappa, Rama et al. (ed.). - Piscataway, NJ : IEEE, 2022. - pp. 3992-4001. - ISSN 1063-6919. - eISSN 2575-7075. - ISBN 978-1-66546-947-0
Abstract
In this work, we present and study a generalized family of differentiable renderers. We discuss from scratch which components are necessary for differentiable rendering and formalize the requirements for each component. We instantiate our general differentiable renderer, which generalizes existing differentiable renderers like SoftRas and DIB-R, with an array of different smoothing distributions to cover a large spectrum of reasonable settings. We evaluate an array of differentiable renderer instantiations on the popular ShapeNet 3D reconstruction benchmark and analyze the implications of our results. Surprisingly, the simple uniform distribution yields the best overall results when averaged over 13 classes; in general, however, the optimal choice of distribution heavily depends on the task.
Summary in another language
Subject (DDC)
004 Computer Science
Keywords
Conference
Conference on Computer Vision and Pattern Recognition (CVPR 2022), Jun 19, 2022 - Jun 24, 2022, New Orleans, Louisiana
Review
undefined / . - undefined, undefined. - (undefined; undefined)
Cite This
ISO 690PETERSEN, Felix, Bastian GOLDLÜCKE, Christian BORGELT, Oliver DEUSSEN, 2022. GenDR : A Generalized Differentiable Renderer. Conference on Computer Vision and Pattern Recognition (CVPR 2022). New Orleans, Louisiana, Jun 19, 2022 - Jun 24, 2022. In: CHELLAPPA, Rama, ed. and others. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, proceedings. Piscataway, NJ:IEEE, pp. 3992-4001. ISSN 1063-6919. eISSN 2575-7075. ISBN 978-1-66546-947-0. Available under: doi: 10.1109/CVPR52688.2022.00397
BibTex
@inproceedings{Petersen2022GenDR-59665,
  year={2022},
  doi={10.1109/CVPR52688.2022.00397},
  title={GenDR : A Generalized Differentiable Renderer},
  isbn={978-1-66546-947-0},
  issn={1063-6919},
  publisher={IEEE},
  address={Piscataway, NJ},
  booktitle={2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, proceedings},
  pages={3992--4001},
  editor={Chellappa, Rama},
  author={Petersen, Felix and Goldlücke, Bastian and Borgelt, Christian and Deussen, Oliver}
}
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/123456789/59665">
    <dc:creator>Petersen, Felix</dc:creator>
    <dc:contributor>Petersen, Felix</dc:contributor>
    <dc:contributor>Deussen, Oliver</dc:contributor>
    <dc:creator>Borgelt, Christian</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-01-10T13:25:06Z</dc:date>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/59665"/>
    <dc:creator>Deussen, Oliver</dc:creator>
    <dc:language>eng</dc:language>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:title>GenDR : A Generalized Differentiable Renderer</dcterms:title>
    <dc:creator>Goldlücke, Bastian</dc:creator>
    <dcterms:issued>2022</dcterms:issued>
    <dc:contributor>Borgelt, Christian</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Goldlücke, Bastian</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:abstract xml:lang="eng">In this work, we present and study a generalized family of differentiable renderers. We discuss from scratch which components are necessary for differentiable rendering and formalize the requirements for each component. We instantiate our general differentiable renderer, which generalizes existing differentiable renderers like SoftRas and DIB-R, with an array of different smoothing distributions to cover a large spectrum of reasonable settings. We evaluate an array of differentiable renderer instantiations on the popular ShapeNet 3D reconstruction benchmark and analyze the implications of our results. Surprisingly, the simple uniform distribution yields the best overall results when averaged over 13 classes; in general, however, the optimal choice of distribution heavily depends on the task.</dcterms:abstract>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-01-10T13:25:06Z</dcterms:available>
  </rdf:Description>
</rdf:RDF>
Internal note
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Contact
URL of original publication
Test date of URL
Examination date of dissertation
Method of financing
Comment on publication
Alliance license
Corresponding Authors der Uni Konstanz vorhanden
International Co-Authors
Bibliography of Konstanz
Yes
Refereed