BFRFormer: Transformer-based generator for Real-World Blind Face Restoration

CASIA OpenIR > 紫东太初大模型研究中心

	BFRFormer: Transformer-based generator for Real-World Blind Face Restoration
	Guojing Ge 1,2; Qi Song3 ; Guibo Zhu1,2,5,6 ; Yuting Zhang 4; Jinglu Chen1 ; Miao Xin1 ; Ming Tang1 ; Jinqiao Wang1,2,6
	2024-04-14
会议名称	2024 IEEE International Conference on Acoustics, Speech and Signal Processing
会议日期	2024年4月14日到2024年4月19日
会议地点	Seoul, Korea
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 is released at https://github.com/s8Znk/BFRFormer.
七大方向——子方向分类	图像视频处理与分析
国重实验室规划方向分类	视觉信息处理
是否有论文关联数据集需要存交	否
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/57281
专题	紫东太初大模型研究中心
作者单位	1.Institute of Automation, Chinese Academy of Sciences 2.Wuhan AI Research 3.Hong Kong Baptist University 4.China Telecom Corporation Ltd 5.Shanghai Artificial Intelligence Laboratory 6.University of Chinese Academy of Sciences
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Guojing Ge,Qi Song,Guibo Zhu,et al. BFRFormer: Transformer-based generator for Real-World Blind Face Restoration[C],2024.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
BFRFormer_Transforme（6872KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载