KOPS - The Institutional Repository of the University of Konstanz

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

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

Cite This

Files in this item

Files Size Format View

There are no files associated with this item.

GIEBENHAIN, Simon, Bastian GOLDLUECKE, 2021. AIR-Nets : An Attention-Based Framework for Locally Conditioned Implicit Representations. International Conference on 3D Vision : 3DV 2021. Online, Dec 1, 2021 - Dec 3, 2021. In: 2021 International Conference on 3D Vision, 3DV 2021 : , virtual conference ; 1-3 December 2021 : proceedings. Piscataway:IEEE, pp. 1054-1064. ISBN 978-1-66542-688-6. Available under: doi: 10.1109/3DV53792.2021.00113

@inproceedings{Giebenhain2021AIRNe-57559, title={AIR-Nets : An Attention-Based Framework for Locally Conditioned Implicit Representations}, year={2021}, doi={10.1109/3DV53792.2021.00113}, isbn={978-1-66542-688-6}, address={Piscataway}, publisher={IEEE}, booktitle={2021 International Conference on 3D Vision, 3DV 2021 : , virtual conference ; 1-3 December 2021 : proceedings}, pages={1054--1064}, author={Giebenhain, Simon and Goldluecke, Bastian} }

<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/rdf/resource/123456789/57559"> <dc:creator>Giebenhain, Simon</dc:creator> <dc:creator>Goldluecke, Bastian</dc:creator> <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> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-05-17T10:51:33Z</dc:date> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dc:contributor>Giebenhain, Simon</dc:contributor> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-05-17T10:51:33Z</dcterms:available> <dcterms:issued>2021</dcterms:issued> <dc:language>eng</dc:language> <dc:contributor>Goldluecke, Bastian</dc:contributor> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/57559"/> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:title>AIR-Nets : An Attention-Based Framework for Locally Conditioned Implicit Representations</dcterms:title> </rdf:Description> </rdf:RDF>

This item appears in the following Collection(s)

Search KOPS


Browse

My Account