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:我们建议一种新型高方字形的面部互换法,名为“Arithmedic Face Swapping” (AFS),该法将一个未经训练的StyGAN的中间潜伏空间 W+ 与中间潜伏空间W+ 分解为“身份”和“风格”子空间,这样W+ 中的潜伏代码就可以将一个“身份”代码和相应的子空间中的“风格”代码相匹配,从而将介于“身份”代码和“风格”代码的中间潜伏空间W+ 中。此外,我们的方法可以概括地将标准面部代码转换为“身份”代码和“风格”代码的总和,从而支持其他有趣的操作,例如,将一个源的身份与多个目标的风格和反之结合起来。我们通过学习一个将隐性代码映射为“风格”代码的神经网络来实施我们的身份风格互换(FSfS) 。我们为这个网络提供了一个条件,这个网络在理论上保证身份特性保护源面面面部/Styfasimal 动作的优势,甚至在我们高级FISFSpeal 的系统上生成的系统上展示了我们的脸结构的系统。