Please report any queries concerning the funding data grouped in the sections named "Externally Awarded" or "Internally Disbursed" (shown on the profile page) to
your Research Finance Administrator. Your can find your Research Finance Administrator at https://www.ucl.ac.uk/finance/research/rs-contacts.php by entering your department
Please report any queries concerning the student data shown on the profile page to:
Email: portico-services@ucl.ac.uk
Help Desk: http://www.ucl.ac.uk/ras/portico/helpdesk
Email: portico-services@ucl.ac.uk
Help Desk: http://www.ucl.ac.uk/ras/portico/helpdesk
Publication Detail
3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch
Feature Swapping for Bodies and Faces
-
Publication Type:Conference
-
Authors:Foti S, Koo B, Stoyanov D, Clarkson MJ
-
Publication date:21/06/2022
-
Name of conference:CVPR 2022
-
Keywords:cs.CV, cs.CV, cs.GR, cs.LG
-
Author URL:
-
Publisher URL:
-
Notes:Accepted for publication at CVPR2022
Abstract
Learning a disentangled, interpretable, and structured latent representation
in 3D generative models of faces and bodies is still an open problem. The
problem is particularly acute when control over identity features is required.
In this paper, we propose an intuitive yet effective self-supervised approach
to train a 3D shape variational autoencoder (VAE) which encourages a
disentangled latent representation of identity features. Curating the
mini-batch generation by swapping arbitrary features across different shapes
allows to define a loss function leveraging known differences and similarities
in the latent representations. Experimental results conducted on 3D meshes show
that state-of-the-art methods for latent disentanglement are not able to
disentangle identity features of faces and bodies. Our proposed method properly
decouples the generation of such features while maintaining good representation
and reconstruction capabilities.
› More search options
UCL Researchers