3D Generative Model Latent Disentanglement via Local Eigenprojection
No Thumbnail Available
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
© 2023 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.
Abstract
Designing realistic digital humans is extremely complex. Most data‐driven generative models used to simplify the creation of their underlying geometric shape do not offer control over the generation of local shape attributes. In this paper, we overcome this limitation by introducing a novel loss function grounded in spectral geometry and applicable to different neural‐network‐based generative models of 3D head and body meshes. Encouraging the latent variables of mesh variational autoencoders (VAEs) or generative adversarial networks (GANs) to follow the local eigenprojections of identity attributes, we improve latent disentanglement and properly decouple the attribute creation. Experimental results show that our local eigenprojection disentangled (LED) models not only offer improved disentanglement with respect to the state‐of‐the‐art, but also maintain good generation capabilities with training times comparable to the vanilla implementations of the models. Our code and pre‐trained models are available at .
Description
@article{10.1111:cgf.14793,
journal = {Computer Graphics Forum},
title = {{3D Generative Model Latent Disentanglement via Local Eigenprojection}},
author = {Foti, Simone and Koo, Bongjin and Stoyanov, Danail and Clarkson, Matthew J.},
year = {2023},
publisher = {© 2023 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.14793}
}