@inproceedings{5560abf3f36848278d7d5feb60913c46,
title = "VariGrad: A Novel Feature Vector Architecture for Geometric Deep Learning on Unregistered Data",
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{\textquoteright}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.",
keywords = "Parametric curve and surface models, Shape analysis",
author = "Emmanuel Hartman and Emery Pierson",
note = "Publisher Copyright: {\textcopyright} 2023 Eurographics Association. All rights reserved.; 16th Eurographics Workshop on 3D Object Retrieval, EG 3DOR 2023 ; Conference date: 31-08-2023 Through 01-09-2023",
year = "2023",
month = jan,
day = "1",
doi = "10.2312/3dor.20231150",
language = "English",
series = "Eurographics Workshop on 3D Object Retrieval, EG 3DOR",
publisher = "Eurographics Association",
pages = "17--23",
editor = "Fellner, \{Dieter W.\} and Werner Hansmann and Werner Purgathofer and Francois Sillion",
booktitle = "EG 3DOR 2023 - Eurographics Workshop on 3D Object Retrieval, Short Papers",
}