Skip to main navigation Skip to search Skip to main content

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We 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.

Original languageEnglish
Title of host publicationEG 3DOR 2023 - Eurographics Workshop on 3D Object Retrieval, Short Papers
EditorsDieter W. Fellner, Werner Hansmann, Werner Purgathofer, Francois Sillion
PublisherEurographics Association
Pages17-23
Number of pages7
ISBN (Electronic)9783038682134
DOIs
Publication statusPublished - 1 Jan 2023
Externally publishedYes
Event16th Eurographics Workshop on 3D Object Retrieval, EG 3DOR 2023 - Lille, France
Duration: 31 Aug 20231 Sept 2023

Publication series

NameEurographics Workshop on 3D Object Retrieval, EG 3DOR
ISSN (Print)1997-0463
ISSN (Electronic)1997-0471

Conference

Conference16th Eurographics Workshop on 3D Object Retrieval, EG 3DOR 2023
Country/TerritoryFrance
CityLille
Period31/08/231/09/23

Keywords

  • Parametric curve and surface models
  • Shape analysis

Fingerprint

Dive into the research topics of 'VariGrad: A Novel Feature Vector Architecture for Geometric Deep Learning on Unregistered Data'. Together they form a unique fingerprint.

Cite this