We propose a novel high-fidelity face swapping method called "Arithmetic Face Swapping" (AFS) that explicitly disentangles the intermediate latent space W+ of a pretrained StyleGAN into the "identity" and "style" subspaces so that a latent code in W+ is the sum of an "identity" code and a "style" code in the corresponding subspaces. Via our disentanglement, face swapping (FS) can be regarded as a simple arithmetic operation in W+, i.e., the summation of a source "identity" code and a target "style" code. This makes AFS more intuitive and elegant than other FS methods. In addition, our method can generalize over the standard face swapping to support other interesting operations, e.g., combining the identity of one source with styles of multiple targets and vice versa. We implement our identity-style disentanglement by learning a neural network that maps a latent code to a "style" code. We provide a condition for this network which theoretically guarantees identity preservation of the source face even after a sequence of face swapping operations. Extensive experiments demonstrate the advantage of our method over state-of-the-art FS methods in producing high-quality swapped faces. Our source code was made public at https://github.com/truongvu2000nd/AFS

翻译：我们提出了一种名为“算术人脸交换”（AFS）的新型高保真人脸交换方法，该方法将预训练StyleGAN的中间潜空间W+显式解耦为“身份”子空间和“风格”子空间，使得W+中的潜码是相应子空间中“身份”码与“风格”码之和。通过解耦，人脸交换可视为W+中的简单算术运算，即源“身份”码与目标“风格”码的求和。这使得AFS比其他方法更直观、更优雅。此外，我们的方法可推广至标准人脸交换之外，支持其他有趣操作，例如将单个源身份与多个目标风格组合，反之亦然。我们通过学习一个将潜码映射到“风格”码的神经网络来实现身份-风格解耦。我们为该网络提供了条件，该条件在理论上保证即使经过一系列人脸交换操作，源人脸的身份仍得以保留。大量实验证明，我们的方法在生成高质量交换人脸方面优于当前最先进的人脸交换方法。我们的源代码已在https://github.com/truongvu2000nd/AFS公开。