Attribute-Specific Manipulation Based on Layer-Wise Channels
This addresses the challenge of precise attribute control in generative models for applications like image editing, though it appears incremental as it builds on existing channel detection techniques.
The paper tackles the problem of disentangling semantic attributes in StyleGAN's latent space for image manipulation by proposing a gradient-based method to detect attribute-specific channels layer by layer. The result is a method that outperforms state-of-the-art approaches in generalization and scalability for face attributes.
Image manipulation on the latent space of the pre-trained StyleGAN can control the semantic attributes of the generated images. Recently, some studies have focused on detecting channels with specific properties to directly manipulate the latent code, which is limited by the entanglement of the latent space. To detect the attribute-specific channels, we propose a novel detection method in the context of pre-trained classifiers. We analyse the gradients layer by layer on the style space. The intensities of the gradients indicate the channel's responses to specific attributes. The latent style codes of channels control separate attributes in the layers. We choose channels with top-$k$ gradients to control specific attributes in the maximum response layer. We implement single-channel and multi-channel manipulations with a certain attribute. Our methods can accurately detect relevant channels for a large number of face attributes. Extensive qualitative and quantitative results demonstrate that the proposed methods outperform state-of-the-art methods in generalization and scalability.