Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation
arXiv:2111.13010 · doi:10.1145/3474085.3475274
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.
ACM MultiMedia 2021.Project: https://wrong.wang/x/Control-Units-in-StyleGAN2/
References in corpus (11)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- GANSpace: Discovering Interpretable GAN Controls
- StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows
- Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
- InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs
- Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis
- Style Intervention: How to Achieve Spatial Disentanglement with Style-based Generators?
- GAN "Steerability" without optimization
- Editing in Style: Uncovering the Local Semantics of GANs
- Unsupervised Discovery of Disentangled Manifolds in GANs
- GuidedStyle: Attribute Knowledge Guided Style Manipulation for Semantic Face Editing