Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation

TL;DR

This paper introduces attribute-specific control units in StyleGAN, enabling fine-grained, spatially precise image manipulation by collaboratively controlling feature maps and modulation styles, outperforming existing methods.

Contribution

It proposes a novel method to detect and manipulate attribute-specific control units in StyleGAN for improved fine-grained image editing.

Findings

Outperforms state-of-the-art methods in face attribute manipulation

Effectively manipulates real images with high precision

Demonstrates superior qualitative and quantitative results

Abstract

Image manipulation with StyleGAN has been an increasing concern in recent years.Recent works have achieved tremendous success in analyzing several semantic latent spaces to edit the attributes of the generated images.However, due to the limited semantic and spatial manipulation precision in these latent spaces, the existing endeavors are defeated in fine-grained StyleGAN image manipulation, i.e., local attribute translation.To address this issue, we discover attribute-specific control units, which consist of multiple channels of feature maps and modulation styles. Specifically, we collaboratively manipulate the modulation style channels and feature maps in control units rather than individual ones to obtain the semantic and spatial disentangled controls. Furthermore, we propose a simple yet effective method to detect the attribute-specific control units. We move the modulation style along a specific sparse direction vector and replace the filter-wise styles used to compute the feature maps to manipulate these control units. We evaluate our proposed method in various face attribute manipulation tasks. Extensive qualitative and quantitative results demonstrate that our proposed method performs favorably against the state-of-the-art methods. The manipulation results of real images further show the effectiveness of our method.