Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. UCLID-Net: Single View Reconstruction in Object Space
 
conference paper

UCLID-Net: Single View Reconstruction in Object Space

Guillard, Benoît  
•
Remelli, Edoardo  
•
Fua, Pascal  
2020
Advances in Neural Information Processing Systems 33
34th Conference on Neural Information Processing Systems

Most state-of-the-art deep geometric learning single-view reconstruction approaches rely on encoder-decoder architectures that output either shape parametrizations or implicit representations. However, these representations rarely preserve the Euclidean structure of the 3D space objects exist in. In this paper, we show that building a geometry preserving 3-dimensional latent space helps the network concurrently learn global shape regularities and local reasoning in the object coordinate space and, as a result, boosts performance.

  • Files
  • Details
  • Metrics
Type
conference paper
Author(s)
Guillard, Benoît  
Remelli, Edoardo  
Fua, Pascal  
Date Issued

2020

Published in
Advances in Neural Information Processing Systems 33
Total of pages

8

Subjects

ml-ai

Editorial or Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
CVLAB  
Event nameEvent placeEvent date
34th Conference on Neural Information Processing Systems

Virtual

December 6-12, 2020

Available on Infoscience
October 28, 2020
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/172816
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés