BFRFormer: Transformer-based generator for Real-World Blind Face Restoration
ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2024)
摘要
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.
更多查看译文
关键词
Blind face restoration,transformer,wavelet discriminator
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要