论文标题
面部交换是一个简单的算术操作
Face Swapping as A Simple Arithmetic Operation
论文作者
论文摘要
我们提出了一种称为“算术面交换”（AFS）的新型高保真面部交换方法，该方法明确地将验证式样式的中间潜在空间W+置于“身份”和“样式”子空间中，以使W+中的潜在代码是“身份”代码和“相应的”代码的总和。通过我们的解开，面部交换（FS）可以被视为W+中的简单算术操作，即，源“身份”代码和目标“样式”代码的总和。这使AFS比其他FS方法更直观和优雅。此外，我们的方法可以概括为标准面部交换以支持其他有趣的操作，例如将一个源的身份与多个目标的样式结合在一起，反之亦然。我们通过学习将潜在代码映射到“样式”代码的神经网络来实现身份风格的分离。我们为该网络提供了一个条件，理论上可以保证即使在一系列面部交换操作之后，也可以保留源面部的身份。广泛的实验证明了我们方法比最先进的FS方法在产生高质量交换面前的优势。我们的源代码在https://github.com/truongvu2000nd/afs上公开
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
