Towards Real-World Blind Face Restoration With Generative Facial Prior

DFDNet ECCV 20 Figure 1: Comparisons with state-of-the-art face restoration methods: HiFaceGAN [67], DFDNet [44], Wan et al. [61] and PULSE [52] on the real-world low-quality images. While previous methods struggle to restore faithful facial details or retain face identity, our proposed GFP-GAN achieves a good balance of realness and fidelity with much less artifacts. In addition, the powerful generative facial prior allows us to perform restoration and color enhancement jointly.