Parameterization Robustness of 3D Auto-Encoders
Loading...
Date
2022
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
The generation of 3-dimensional geometric objects in the most efficient way is a thriving research topic with, for example, the development of geometric deep learning, extending classical machine learning concepts to non euclidean data such as graphs or meshes. In this short paper, we study the effect of a reparameterization on two popular mesh and point cloud neural networks in an auto-encoder mode: PointNet [QSMG16] and SpiralNet [BBP∗19]. Finally, we tested a modified version of PointNet that takes orientation into account (through coordinates of the normals) as a first step towards the construction of a geometric deep learning model built with a more flexible metric regarding the parameterization. The experimental results on standardized face datasets show that SpiralNet is more robust to the reparametrization than PointNet in this specific context with the proposed reparameterization.
Description
CCS Concepts: Deep learning → 3D generative models; Performance measure → Reparameterization; Robustness
@inproceedings{10.2312:3dor.20221180,
booktitle = {Eurographics Workshop on 3D Object Retrieval},
editor = {Berretti, Stefano and Thehoaris, Theoharis and Daoudi, Mohamed and Ferrari, Claudio and Veltkamp, Remco C.},
title = {{Parameterization Robustness of 3D Auto-Encoders}},
author = {Pierson, Emery and Besnier, Thomas and Daoudi, Mohamed and Arguillère, Sylvain},
year = {2022},
publisher = {The Eurographics Association},
ISSN = {1997-0471},
ISBN = {978-3-03868-174-8},
DOI = {10.2312/3dor.20221180}
}