GuidedStyle: Attribute knowledge guided style manipulation for semantic face editing. (January 2022)

• Record Type: Journal Article
• Authors: Hou, Xianxu; Zhang, Xiaokang; Liang, Hanbang; Shen, Linlin; Lai, Zhihui; Wan, Jun
• Is Part Of: Neural networks. Volume 145(2022)
• Page Start: 209
• Page End: 220
• Publication Date: 2022-01
• Subjects: Generative Adversarial Networks -- StyleGAN -- Semantic face editing; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2021.10.017
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Although significant progress has been made in synthesizing high-quality and visually realistic face images by unconditional Generative Adversarial Networks (GANs), there is still a lack of control over the generation process in order to achieve semantic face editing. In this paper, we propose a novel learning framework, called GuidedStyle, to achieve semantic face editing on pretrained 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, hair color and attractive. 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.