VR-FAM: VARIANCE-REDUCED ENCODER WITH NONLINEAR TRANSFORMATION FOR FACIAL ATTRIBUTE MANIPULATION

Facial attribute manipulation (FAM) aims to infer desired facial images by modifying specific attributes while keeping others unchanged. Existing works suffer from the entanglement of facial attributes, leading to unexpected artifacts and the loss of facial identity information after editing. To alleviate these issues, we propose a novel FAM framework based on Sty1eGAN, termed VR-FAM, which can meet the requirements of FAM-editing ability, distortion, and fidelity. First, we propose a variance-reduced encoder to make the latent space close to the one of Sty1eGAN. Second, we present a nonlinear latent transformation network, which can convert the source latent code to target latent code in line with the nonlinear latent space of StyleGAN. Experimentally, we evaluate the proposed FAM framework on the benchmark FFHQ dataset and demonstrate the improvement gain over the recently published models in terms of edit accuracy and fidelity.