FaceController: Controllable Attribute Editing for Face in the Wild
This work addresses controllable face editing for applications like face swapping and makeup transfer, but it is incremental as it builds on prior disentanglement methods.
The authors tackled face attribute editing by proposing a feed-forward network that uses 3D priors and region-wise style codes to decouple identity, expression, pose, and illumination, achieving the best or competitive scores on various face applications.
Face attribute editing aims to generate faces with one or multiple desired face attributes manipulated while other details are preserved. Unlike prior works such as GAN inversion, which has an expensive reverse mapping process, we propose a simple feed-forward network to generate high-fidelity manipulated faces. By simply employing some existing and easy-obtainable prior information, our method can control, transfer, and edit diverse attributes of faces in the wild. The proposed method can consequently be applied to various applications such as face swapping, face relighting, and makeup transfer. In our method, we decouple identity, expression, pose, and illumination using 3D priors; separate texture and colors by using region-wise style codes. All the information is embedded into adversarial learning by our identity-style normalization module. Disentanglement losses are proposed to enhance the generator to extract information independently from each attribute. Comprehensive quantitative and qualitative evaluations have been conducted. In a single framework, our method achieves the best or competitive scores on a variety of face applications.