Multi-Directional Subspace Editing in Style-Space

TL;DR

This paper introduces a novel technique for disentangled, multi-directional editing of face attributes in StyleGAN's latent space, improving attribute control and separation.

Contribution

It presents a method to identify orthogonal semantic subspaces enabling precise, multi-directional attribute editing with better disentanglement than existing models.

Findings

Outperforms state-of-the-art models in face attribute editing

Provides quantitative measures for attribute separation

Demonstrates effective multi-directional attribute control

Abstract

This paper describes a new technique for finding disentangled semantic directions in the latent space of StyleGAN. Our method identifies meaningful orthogonal subspaces that allow editing of one human face attribute, while minimizing undesired changes in other attributes. Our model is capable of editing a single attribute in multiple directions, resulting in a range of possible generated images. We compare our scheme with three state-of-the-art models and show that our method outperforms them in terms of face editing and disentanglement capabilities. Additionally, we suggest quantitative measures for evaluating attribute separation and disentanglement, and exhibit the superiority of our model with respect to those measures.