GuidedStyle: Attribute Knowledge Guided Style Manipulation for Semantic Face Editing
This work provides improved disentangled and controllable semantic face editing for users and applications requiring precise manipulation of facial attributes, representing an incremental improvement in the field.
This paper addresses the lack of control in unconditional GANs for semantic face editing, proposing GuidedStyle to guide StyleGAN's generation with a knowledge network. The method enables disentangled and controllable edits for various attributes like smiling, eyeglasses, gender, mustache, and hair color, outperforming competing methods qualitatively and quantitatively.
Although significant progress has been made in synthesizing high-quality and visually realistic face images by unconditional Generative Adversarial Networks (GANs), there still lacks of control over the generation process in order to achieve semantic face editing. In addition, it remains very challenging to maintain other face information untouched while editing the target attributes. In this paper, we propose a novel learning framework, called GuidedStyle, to achieve semantic face editing on StyleGAN by guiding the image generation process with a knowledge network. Furthermore, we allow an attention mechanism in StyleGAN generator to adaptively select a single layer for style manipulation. As a result, our method is able to perform disentangled and controllable edits along various attributes, including smiling, eyeglasses, gender, mustache and hair color. Both qualitative and quantitative results demonstrate the superiority of our method over other competing methods for semantic face editing. Moreover, we show that our model can be also applied to different types of real and artistic face editing, demonstrating strong generalization ability.