Progressive Semantic-Aware Style Transformation for Blind Face Restoration

HiFaceGAN [36] DFDNet [20] Ours * This work was done when he was an intern at Alibaba. real-world LQ face images. Experiment results show that our model trained with synthetic data can not only produce more realistic high-resolution results for synthetic LQ inputs but also generalize better to natural LQ face images compared with state-of-the-art methods.