ITU

Tensor-based Subspace Factorization for StyleGAN

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

View graph of relations

In this paper, we propose tGAN a tensor-based method for modeling the latent space of generative models.
The objective is to identify semantic directions in latent space.
To this end, we propose to fit a multilinear tensor model on a structured facial expression database, which is initially embedded into latent space.
We validate our approach on StyleGAN trained on FFHQ using BU-3DFE as a structured facial expression database.
We show how the parameters of the multilinear tensor model can be approximated by Alternating Least Squares.
Further, we introduce a stacked style-separated tensor model, defined as an ensemble of style-specific models to integrate our approach with the extended latent space of StyleGAN.
We show that taking the individual styles of the extended latent space into account leads to higher model flexibility and lower reconstruction error.
Finally, we do several experiments comparing our approach to former work on both GANs and multilinear models.
Concretely, we analyze the expression subspace and find that the expression trajectories meet at an apathetic face that is consistent with earlier work.
We also show that by changing the pose of a person, the generated image from our approach is closer to the ground truth than results from two competing approaches.
Original languageEnglish
Title of host publicationIEEE International Conference on Automatic Face and Gesture Recognition 2021
Publication dateDec 2021
Publication statusPublished - Dec 2021

Bibliographical note

Doesn't seem to count as OA? (jcg: 14/02/2022)

Close

    Research areas

  • StyleGAN, tensor model

ID: 86353680