Log In Sign Up

Unsupervised Disentanglement of Linear-Encoded Facial Semantics

by   Yutong Zheng, et al.

We propose a method to disentangle linear-encoded facial semantics from StyleGAN without external supervision. The method derives from linear regression and sparse representation learning concepts to make the disentangled latent representations easily interpreted as well. We start by coupling StyleGAN with a stabilized 3D deformable facial reconstruction method to decompose single-view GAN generations into multiple semantics. Latent representations are then extracted to capture interpretable facial semantics. In this work, we make it possible to get rid of labels for disentangling meaningful facial semantics. Also, we demonstrate that the guided extrapolation along the disentangled representations can help with data augmentation, which sheds light on handling unbalanced data. Finally, we provide an analysis of our learned localized facial representations and illustrate that the semantic information is encoded, which surprisingly complies with human intuition. The overall unsupervised design brings more flexibility to representation learning in the wild.


page 13

page 19

page 21

page 22

page 23

page 24

page 25

page 26


The pursuit of beauty: Converting image labels to meaningful vectors

A challenge of the computer vision community is to understand the semant...

Equivariant Representation Learning via Class-Pose Decomposition

We introduce a general method for learning representations that are equi...

Linear Disentangled Representations and Unsupervised Action Estimation

Disentangled representation learning has seen a surge in interest over r...

Towards Disentangled Representations for Human Retargeting by Multi-view Learning

We study the problem of learning disentangled representations for data a...

Where and What? Examining Interpretable Disentangled Representations

Capturing interpretable variations has long been one of the goals in dis...

LARGE: Latent-Based Regression through GAN Semantics

We propose a novel method for solving regression tasks using few-shot or...