One Shot Face Swapping on Megapixels

TL;DR

This paper introduces MegaFS, a novel megapixel-level one-shot face swapping method that maintains detailed facial features, enables stable training with limited memory, and provides a large dataset for DeepFake detection research.

Contribution

The paper presents the first megapixel-level face swapping method with hierarchical face representation, a non-linear identity transfer module, and a large public dataset for research.

Findings

MegaFS achieves superior face swapping quality at megapixel resolution.

The method enables stable training with limited GPU memory.

A large, publicly available dataset supports DeepFake detection research.

Abstract

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. The dataset is at this link.