Skip to main navigation Skip to search Skip to main content

Toward Mesh-Invariant 3D Generative Deep Learning with Geometric Measures

  • Thomas Besnier
  • , Sylvain Arguillère
  • , Emery Pierson
  • , Mohamed Daoudi

Research output: Contribution to journalArticlepeer-review

Abstract

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.

Original languageEnglish
Pages (from-to)309-320
Number of pages12
JournalComputers and Graphics (Pergamon)
Volume115
DOIs
Publication statusPublished - 1 Oct 2023
Externally publishedYes

Keywords

  • 3D generative model
  • Geometric measures
  • Unsupervised learning

Fingerprint

Dive into the research topics of 'Toward Mesh-Invariant 3D Generative Deep Learning with Geometric Measures'. Together they form a unique fingerprint.

Cite this