• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Scopus
  4. Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes
 
  • Details
  • Full
Options
2022
Conference Paper
Title

Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes

Abstract
The analysis of deforming 3D surface meshes is accelerated by autoencoders since the low-dimensional embeddings can be used to visualize underlying dynamics. But, state-of-the-art mesh convolutional autoencoders require a fixed connectivity of all input meshes handled by the autoencoder. This is due to either the use of spectral convolutional layers or mesh dependent pooling operations. Therefore, the types of datasets that one can study are limited and the learned knowledge cannot be transferred to other datasets that exhibit similar behavior. To address this, we transform the discretization of the surfaces to semi-regular meshes that have a locally regular connectivity and whose meshing is hierarchical. This allows us to apply the same spatial convolutional filters to the local neighborhoods and to define a pooling operator that can be applied to every semi-regular mesh. We apply the same mesh autoencoder to different datasets and our reconstruction error is more than 50% lower than the error from state-of-the-art models, which have to be trained for every mesh separately. Additionally, we visualize the underlying dynamics of unseen mesh sequences with an autoencoder trained on different classes of meshes.
Author(s)
Hahner, Sara  
Fraunhofer-Institut für Algorithmen und Wissenschaftliches Rechnen SCAI  
Garcke, Jochen  
Fraunhofer-Institut für Algorithmen und Wissenschaftliches Rechnen SCAI  
Mainwork
IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022. Proceedings  
Conference
Winter Conference on Applications of Computer Vision (WACV) 2022  
Open Access
DOI
10.1109/WACV51458.2022.00240
Language
English
Fraunhofer-Institut für Algorithmen und Wissenschaftliches Rechnen SCAI  
Keyword(s)
  • Autoencoders

  • Deep Learning

  • Few-shot

  • GANs

  • Graph Neural Networks 3D Computer Vision

  • Neural Generative Models

  • Semi- and Un- supervised Learning

  • Transfer

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024