Toward Mesh-Invariant 3D Generative Deep ...
Document type :
Article dans une revue scientifique: Article original
Title :
Toward Mesh-Invariant 3D Generative Deep Learning with Geometric Measures
Author(s) :
Besnier, Thomas [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Arguillère, Sylvain [Auteur]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
Pierson, Emery [Auteur]
Universität Wien = University of Vienna
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Daoudi, Mohamed [Auteur]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Nord Europe]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Arguillère, Sylvain [Auteur]

Laboratoire Paul Painlevé - UMR 8524 [LPP]
Pierson, Emery [Auteur]
Universität Wien = University of Vienna
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Daoudi, Mohamed [Auteur]

Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Nord Europe]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Journal title :
Computers and Graphics
Publisher :
Elsevier
Publication date :
2023
ISSN :
0097-8493
English keyword(s) :
3D generative model
Unsupervised learning
Geometric measures
Unsupervised learning
Geometric measures
HAL domain(s) :
Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
Mathématiques [math]
Mathématiques [math]
English abstract : [en]
3D generative modeling is accelerating as the technology allowing the capture of geometric data is developing. However, the acquired data is often inconsistent, resulting in unregistered meshes or point clouds. Many ...
Show more >3D generative modeling is accelerating as the technology allowing the capture of geometric data is developing. However, the acquired data is often inconsistent, resulting in unregistered meshes or point clouds. Many generative learning algorithms require correspondence between each point when comparing the predicted shape and the target shape. We propose an architecture able to cope with different parameterizations, even during the training phase. In particular, our loss function is built upon a kernel-based metric over a representation of meshes using geometric measures such as currents and varifolds. The latter allows to implement an efficient dissimilarity measure with many desirable properties such as robustness to resampling of the mesh or point cloud. We demonstrate the efficiency and resilience of our model with a generative learning task of human faces.Show less >
Show more >3D generative modeling is accelerating as the technology allowing the capture of geometric data is developing. However, the acquired data is often inconsistent, resulting in unregistered meshes or point clouds. Many generative learning algorithms require correspondence between each point when comparing the predicted shape and the target shape. We propose an architecture able to cope with different parameterizations, even during the training phase. In particular, our loss function is built upon a kernel-based metric over a representation of meshes using geometric measures such as currents and varifolds. The latter allows to implement an efficient dissimilarity measure with many desirable properties such as robustness to resampling of the mesh or point cloud. We demonstrate the efficiency and resilience of our model with a generative learning task of human faces.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- 2306.15762
- Open access
- Access the document