One Shot Face Swapping on Megapixels

By Yuhao Zhu, Qi Li, Jian Wang, Chengzhong Xu, Zhenan Sun. 2021

205 citations recorded by the source corpus.

Face swapping has both positive applications such as entertainment, human-computer interaction, etc., and negative applications such as DeepFake threats to politics, economics, etc. Nevertheless, it is necessary to understand the scheme of advanced methods for high-quality face swapping and generate enough and representative face swapping images to train DeepFake detection algorithms. This paper proposes the first Megapixel level method for one shot Face Swapping (or MegaFS for short). Firstly, MegaFS organizes face representation hierarchically by the proposed Hierarchical Representation Face Encoder (HieRFE) in an extended latent space to maintain more facial details, rather than compressed representation in previous face swapping methods. Secondly, a carefully designed Face Transfer Module (FTM) is proposed to transfer the identity from a source image to the target by a non-linear trajectory without explicit feature disentanglement. Finally, the swapped faces can be synthesized by StyleGAN2 with the benefits of its training stability and powerful generative capability. Each part of MegaFS can be trained separately so the requirement of our model for GPU memory can be satisfied for megapixel face swapping. In summary, complete face representation, stable training, and limited memory usage are the three novel contributions to the success of our method. Extensive experiments demonstrate the superiority of MegaFS and the first megapixel level face swapping database is released for research on DeepFake detection and face image editing in the public domain.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Yujiu Yang
2. Weihao Xia
3. Fei Yin
4. Qingyan Bai
5. Jing-Hao Xue
6. Chenglin Liu

Citations in the corpus

• Identity-Guided Face Generation with Multi-Modal Contour Conditions (2021, background): “To enlarge capacity of latent space and preserve spatial information, the last block of the main encoder predicts not only a classic 18×512 W style latent code [8] but a 4×4×512 input latent code [16].”