FSNet: An Identity-Aware Generative Model for Image-based Face Swapping
This work addresses face swapping for image editing applications, offering an incremental improvement over existing methods by avoiding 3D model fitting.
The paper tackles the problem of face swapping in images by introducing FSNet, a deep generative model that uses a latent variable representation instead of traditional 3D morphable models, resulting in more stable performance and compatibility with state-of-the-art methods under challenging conditions like varying face orientations and lighting.
This paper presents FSNet, a deep generative model for image-based face swapping. Traditionally, face-swapping methods are based on three-dimensional morphable models (3DMMs), and facial textures are replaced between the estimated three-dimensional (3D) geometries in two images of different individuals. However, the estimation of 3D geometries along with different lighting conditions using 3DMMs is still a difficult task. We herein represent the face region with a latent variable that is assigned with the proposed deep neural network (DNN) instead of facial textures. The proposed DNN synthesizes a face-swapped image using the latent variable of the face region and another image of the non-face region. The proposed method is not required to fit to the 3DMM; additionally, it performs face swapping only by feeding two face images to the proposed network. Consequently, our DNN-based face swapping performs better than previous approaches for challenging inputs with different face orientations and lighting conditions. Through several experiments, we demonstrated that the proposed method performs face swapping in a more stable manner than the state-of-the-art method, and that its results are compatible with the method thereof.