VariGrad: A Novel Feature Vector Architecture for Geometric Deep Learning on Unregistered Data
No Thumbnail Available
Date
2023
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
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.
Description
CCS Concepts: Computing methodologies → Parametric curve and surface models; Shape analysis
@inproceedings{10.2312:3dor.20231150,
booktitle = {Eurographics Workshop on 3D Object Retrieval},
editor = {Fugacci, Ulderico and Lavoué, Guillaume and Veltkamp, Remco C.},
title = {{VariGrad: A Novel Feature Vector Architecture for Geometric Deep Learning on Unregistered Data}},
author = {Hartman, Emmanuel and Pierson, Emery},
year = {2023},
publisher = {The Eurographics Association},
ISSN = {1997-0471},
ISBN = {978-3-03868-213-4},
DOI = {10.2312/3dor.20231150}
}