TY - GEN
T1 - Parameterization Robustness of 3D Auto-Encoders
AU - Pierson, E.
AU - Besnier, T.
AU - Daoudi, M.
AU - Arguillère, S.
N1 - Publisher Copyright:
© 2022 The Author(s) Eurographics Proceedings © 2022 The Eurographics Association.
PY - 2022/1/1
Y1 - 2022/1/1
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85159782907
U2 - 10.2312/3dor.20221180
DO - 10.2312/3dor.20221180
M3 - Conference contribution
AN - SCOPUS:85159782907
T3 - Eurographics Workshop on 3D Object Retrieval, EG 3DOR
SP - 17
EP - 23
BT - EG 3DOR 2022 - Eurographics Workshop on 3D Object Retrieval Short Papers
A2 - Fellner, Dieter W.
A2 - Hansmann, Werner
A2 - Purgathofer, Werner
A2 - Sillion, Francois
PB - Eurographics Association
T2 - 2022 Eurographics Workshop on 3D Object Retrieval, EG 3DOR 2022
Y2 - 1 September 2022 through 2 September 2022
ER -