FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping
This work addresses the challenge of realistic face swapping in images, particularly for applications in entertainment and media, but it is incremental as it builds upon existing face swapping techniques.
The paper tackles the problem of generating high-fidelity and occlusion-aware face swapping by proposing a two-stage framework called FaceShifter, which integrates target attributes adaptively and refines occlusions without manual annotations, resulting in more perceptually appealing and identity-preserving outcomes compared to state-of-the-art methods.
In this work, we propose a novel two-stage framework, called FaceShifter, for high fidelity and occlusion aware face swapping. Unlike many existing face swapping works that leverage only limited information from the target image when synthesizing the swapped face, our framework, in its first stage, generates the swapped face in high-fidelity by exploiting and integrating the target attributes thoroughly and adaptively. We propose a novel attributes encoder for extracting multi-level target face attributes, and a new generator with carefully designed Adaptive Attentional Denormalization (AAD) layers to adaptively integrate the identity and the attributes for face synthesis. To address the challenging facial occlusions, we append a second stage consisting of a novel Heuristic Error Acknowledging Refinement Network (HEAR-Net). It is trained to recover anomaly regions in a self-supervised way without any manual annotations. Extensive experiments on wild faces demonstrate that our face swapping results are not only considerably more perceptually appealing, but also better identity preserving in comparison to other state-of-the-art methods.