FaceController: Controllable Attribute Editing for Face in the Wild

23 Feb 2021  ·  Zhiliang Xu, Xiyu Yu, Zhibin Hong, Zhen Zhu, Junyu Han, Jingtuo Liu, Errui Ding, Xiang Bai ·

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.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Face Swapping FaceForensics++ FaceController FID 3.51 # 1
Face Swapping FaceForensics++ FaceShifter FID 4.05 # 3
Face Swapping FaceForensics++ FSGAN FID 4.35 # 5
Face Swapping FaceForensics++ FaceSwap FID 3.81 # 2
Face Swapping FaceForensics++ DeepFake FID 4.29 # 4


No methods listed for this paper. Add relevant methods here