VariGrad: A Novel Feature Vector Architecture for Geometric Deep Learning on Unregistered Data

Simple item page
dc.contributor.authorHartman, Emmanuelen_US
dc.contributor.authorPierson, Emeryen_US
dc.contributor.editorFugacci, Uldericoen_US
dc.contributor.editorLavoué, Guillaumeen_US
dc.contributor.editorVeltkamp, Remco C.en_US
dc.date.accessioned2023-08-30T05:51:33Z
dc.date.available2023-08-30T05:51:33Z
dc.date.issued2023
dc.description.abstractWe present a novel geometric deep learning layer that leverages the varifold gradient (VariGrad) to compute feature vector representations of 3D geometric data. These feature vectors can be used in a variety of downstream learning tasks such as classification, registration, and shape reconstruction. Our model's use of parameterization independent varifold representations of geometric data allows our model to be both trained and tested on data independent of the given sampling or parameterization. We demonstrate the efficiency, generalizability, and robustness to resampling demonstrated by the proposed VariGrad layer.en_US
dc.description.sectionheadersShort Papers
dc.description.seriesinformationEurographics Workshop on 3D Object Retrieval
dc.identifier.doi10.2312/3dor.20231150
dc.identifier.isbn978-3-03868-213-4
dc.identifier.issn1997-0471
dc.identifier.pages17-23
dc.identifier.pages7 pages
dc.identifier.urihttps://doi.org/10.2312/3dor.20231150
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/3dor20231150
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Parametric curve and surface models; Shape analysis
dc.subjectComputing methodologies → Parametric curve and surface models
dc.subjectShape analysis
dc.titleVariGrad: A Novel Feature Vector Architecture for Geometric Deep Learning on Unregistered Dataen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
017-023.pdf
Size:
2.12 MB
Format:
Adobe Portable Document Format
Download
Collections
3DOR 2023 - Short Papers