ExtSwap: Leveraging Extended Latent Mapper for Generating High Quality Face Swapping
This addresses the problem of generating high-quality face-swapped images for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of entangled representations in face swapping by proposing a method that disentangles identity and attribute features separately, then maps them into StyleGAN's extended latent space. The method outperforms state-of-the-art face swapping methods both qualitatively and quantitatively.
We present a novel face swapping method using the progressively growing structure of a pre-trained StyleGAN. Previous methods use different encoder decoder structures, embedding integration networks to produce high-quality results, but their quality suffers from entangled representation. We disentangle semantics by deriving identity and attribute features separately. By learning to map the concatenated features into the extended latent space, we leverage the state-of-the-art quality and its rich semantic extended latent space. Extensive experiments suggest that the proposed method successfully disentangles identity and attribute features and outperforms many state-of-the-art face swapping methods, both qualitatively and quantitatively.