BFRFormer: Transformer-based generator for Real-World Blind Face Restoration
This addresses the problem of restoring degraded face images while preserving identity details for applications in computer vision, though it is incremental as it adapts Transformers to an existing task.
The authors tackled blind face restoration, which suffers from over-smoothed results and loss of identity details due to short-range dependencies in CNNs, by proposing BFRFormer, a Transformer-based method that outperformed state-of-the-art methods on synthetic and real-world datasets.
Blind face restoration is a challenging task due to the unknown and complex degradation. Although face prior-based methods and reference-based methods have recently demonstrated high-quality results, the restored images tend to contain over-smoothed results and lose identity-preserved details when the degradation is severe. It is observed that this is attributed to short-range dependencies, the intrinsic limitation of convolutional neural networks. To model long-range dependencies, we propose a Transformer-based blind face restoration method, named BFRFormer, to reconstruct images with more identity-preserved details in an end-to-end manner. In BFRFormer, to remove blocking artifacts, the wavelet discriminator and aggregated attention module are developed, and spectral normalization and balanced consistency regulation are adaptively applied to address the training instability and over-fitting problem, respectively. Extensive experiments show that our method outperforms state-of-the-art methods on a synthetic dataset and four real-world datasets. The source code, Casia-Test dataset, and pre-trained models are released at https://github.com/s8Znk/BFRFormer.