FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment. Better Subject Agnostic Face Swapping and Reenactment

We present Face Swapping GAN (FSGAN) for face swapping and reenactment. Unlike previous work, we offer a subject agnostic swapping scheme that can be applied to pairs of faces without requiring training using those faces. We derive a novel iterative deep learning based approach for face reenactment which adjusts significant pose and expression variations that can be applied to a single image or a video sequence. For video sequences, we introduce continuous interpolation of the face views based on reenactment, Delaunay Triangulation, and barycentric coordinates. Occluded face regions are handled by a face completion network. Finally, we use a face blending network for seamless blending of the two faces while preserving the target skin color and lighting conditions. This network uses a novel Poisson blending loss combining Poisson optimization with a perceptual loss. We compare our approach to existing state-of-the-art systems and show our results to be both qualitatively and quantitatively superior. This work describes extensions of the FSGAN method, proposed in an earlier, conference version of our work [1], as well as additional experiments and results.