Transforming Facial Weight of Real Images by Editing Latent Space of StyleGAN

TL;DR

This paper introduces a method to automatically modify facial weight in images by editing the latent space of StyleGAN, enabling realistic transformations without retraining the GAN.

Contribution

We propose an invert-and-edit framework that leverages semantic attribute directions in StyleGAN's latent space for facial weight modification, avoiding extensive retraining.

Findings

Produces high-quality, realistic weight transformations

Does not require retraining GANs with large labeled datasets

Effective for visualizing future appearance changes

Abstract

We present an invert-and-edit framework to automatically transform facial weight of an input face image to look thinner or heavier by leveraging semantic facial attributes encoded in the latent space of Generative Adversarial Networks (GANs). Using a pre-trained StyleGAN as the underlying generator, we first employ an optimization-based embedding method to invert the input image into the StyleGAN latent space. Then, we identify the facial-weight attribute direction in the latent space via supervised learning and edit the inverted latent code by moving it positively or negatively along the extracted feature axis. Our framework is empirically shown to produce high-quality and realistic facial-weight transformations without requiring training GANs with a large amount of labeled face images from scratch. Ultimately, our framework can be utilized as part of an intervention to motivate individuals to make healthier food choices by visualizing the future impacts of their behavior on appearance.