FaceFormer: Scale-aware Blind Face Restoration with Transformers
This addresses the limitation of most current works that support only specific scale faces, improving application in real-world scenarios.
The paper tackles the problem of blind face restoration for diverse scale inputs, proposing FaceFormer which adapts to arbitrary face scales and achieves better generalization to natural low-quality images than current state-of-the-art methods.
Blind face restoration usually encounters with diverse scale face inputs, especially in the real world. However, most of the current works support specific scale faces, which limits its application ability in real-world scenarios. In this work, we propose a novel scale-aware blind face restoration framework, named FaceFormer, which formulates facial feature restoration as scale-aware transformation. The proposed Facial Feature Up-sampling (FFUP) module dynamically generates upsampling filters based on the original scale-factor priors, which facilitate our network to adapt to arbitrary face scales. Moreover, we further propose the facial feature embedding (FFE) module which leverages transformer to hierarchically extract diversity and robustness of facial latent. Thus, our FaceFormer achieves fidelity and robustness restored faces, which possess realistic and symmetrical details of facial components. Extensive experiments demonstrate that our proposed method trained with synthetic dataset generalizes better to a natural low quality images than current state-of-the-arts.