Representation learning of 3D meshes using an Autoencoder in the spectral domain - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2022

Representation learning of 3D meshes using an Autoencoder in the spectral domain

Clément Lemeunier
Florence Denis
Guillaume Lavoué
Florent Dupont

Abstract

Learning on surfaces is a difficult task: the data being non-Euclidean makes the transfer of known techniques such as convolutions and pooling non trivial. Common methods deploy processes to apply deep learning operations to triangular meshes either in the spatial domain by defining weights between nodes, or in the spectral domain using first order Chebyshev polynomials followed by a return in the spatial domain. In this study, we present a Spectral Autoencoder (SAE) enabling the application of deep learning techniques to 3D meshes by directly giving spectral coefficients obtained with a spectral transform as inputs. With a dataset composed of surfaces having the same connectivity, it is possible with the Graph Laplacian to express the geometry of all samples in the frequency domain. Then, by using an Autoencoder architecture, we are able to extract important features from spectral coefficients without going back to the spatial domain. Finally, a latent space is built from which reconstruction and interpolation is possible. This method allows the treatment of meshes with more vertices by keeping the same architecture, and allows to learn on big datasets with short computation times. Through experiments, we demonstrate that this architecture is able to give better results than state of the art methods in a faster way.
Fichier principal
Vignette du fichier
Representation_learning_of_3D_meshes_using_an_Autoencoder_in_the_spectral_domain.pdf (12.05 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03716435 , version 1 (08-07-2022)
hal-03716435 , version 2 (15-09-2022)
hal-03716435 , version 3 (06-04-2023)

Identifiers

Cite

Clément Lemeunier, Florence Denis, Guillaume Lavoué, Florent Dupont. Representation learning of 3D meshes using an Autoencoder in the spectral domain. 2022. ⟨hal-03716435v2⟩
191 View
868 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More