Tensor-based Subspace Factorization for StyleGAN

TL;DR

This paper introduces τGAN, a tensor-based method for modeling and manipulating the latent space of StyleGAN to better understand and control facial expressions and poses, achieving improved accuracy over previous methods.

Contribution

The paper presents a novel tensor-based approach for modeling StyleGAN's latent space, including a style-separated tensor model that enhances flexibility and reduces reconstruction error.

Findings

Expression trajectories converge at an apathetic face, consistent with prior work.

Changing pose results in generated images closer to ground truth.

The approach outperforms previous methods in expression and pose modeling.

Abstract

In this paper, we propose $\tau$GAN 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 tacked 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.