Expanding the Latent Space of StyleGAN for Real Face Editing

TL;DR

This paper introduces a two-branch model to expand StyleGAN's latent space, improving real face editing by balancing identity preservation and meaningful manipulation.

Contribution

It proposes a novel two-branch approach that enhances StyleGAN's latent space for better real face editing and reconstruction.

Findings

Improved identity preservation in face editing.

Enhanced balance between editability and appearance fidelity.

Validated effectiveness through extensive experiments.

Abstract

Recently, a surge of face editing techniques have been proposed to employ the pretrained StyleGAN for semantic manipulation. To successfully edit a real image, one must first convert the input image into StyleGAN's latent variables. However, it is still challenging to find latent variables, which have the capacity for preserving the appearance of the input subject (e.g., identity, lighting, hairstyles) as well as enabling meaningful manipulations. In this paper, we present a method to expand the latent space of StyleGAN with additional content features to break down the trade-off between low-distortion and high-editability. Specifically, we proposed a two-branch model, where the style branch first tackles the entanglement issue by the sparse manipulation of latent codes, and the content branch then mitigates the distortion issue by leveraging the content and appearance details from the input image. We confirm the effectiveness of our method using extensive qualitative and quantitative experiments on real face editing and reconstruction tasks.