Simple Baselines for Image Restoration

被引:621
作者
Chen, Liangyu [1 ]
Chu, Xiaojie [1 ]
Zhang, Xiangyu [1 ]
Sun, Jian [1 ]
机构
[1] MEGVII Technol, Beijing, Peoples R China
来源
COMPUTER VISION, ECCV 2022, PT VII | 2022年 / 13667卷
基金
国家重点研发计划;
关键词
Image restoration; Image denoise; Image deblur;
D O I
10.1007/978-3-031-20071-7_2
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Although there have been significant advances in the field of image restoration recently, the system complexity of the state-of-the-art (SOTA) methods is increasing as well, which may hinder the convenient analysis and comparison of methods. In this paper, we propose a simple baseline that exceeds the SOTA methods and is computationally efficient. To further simplify the baseline, we reveal that the nonlinear activation functions, e.g. Sigmoid, ReLU, GELU, Softmax, etc. are not necessary: they could be replaced by multiplication or removed. Thus, we derive a Nonlinear Activation Free Network, namely NAFNet, from the baseline. SOTA results are achieved on various challenging benchmarks, e.g. 33.69 dB PSNR on GoPro (for image deblurring), exceeding the previous SOTA 0.38 dB with only 8.4% of its computational costs; 40.30 dB PSNR on SIDD (for image denoising), exceeding the previous SOTA 0.28 dB with less than half of its computational costs. The code and the pre-trained models are released at github.com/megvii-research/NAFNet.
引用
收藏
页码:17 / 33
页数:17
相关论文
共 38 条
[1]   A High-Quality Denoising Dataset for Smartphone Cameras [J].
Abdelhamed, Abdelrahman ;
Lin, Stephen ;
Brown, Michael S. .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :1692-1700
[2]  
Ba J. L., 2016, arXiv, DOI 10.48550/arXiv:1607.06450
[3]   Pre-Trained Image Processing Transformer [J].
Chen, Hanting ;
Wang, Yunhe ;
Guo, Tianyu ;
Xu, Chang ;
Deng, Yiping ;
Liu, Zhenhua ;
Ma, Siwei ;
Xu, Chunjing ;
Xu, Chao ;
Gao, Wen .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :12294-12305
[4]   HINet: Half Instance Normalization Network for Image Restoration [J].
Chen, Liangyu ;
Lu, Xin ;
Zhang, Jie ;
Chu, Xiaojie ;
Chen, Chengpeng .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021, 2021, :182-192
[5]   NBNet: Noise Basis Learning for Image Denoising with Subspace Projection [J].
Cheng, Shen ;
Wang, Yuzhi ;
Huang, Haibin ;
Liu, Donghao ;
Fan, Haoqiang ;
Liu, Shuaicheng .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :4894-4904
[6]  
Cho S.J., 2021, P IEEECVF INT C COMP, P4641
[7]  
Chu XJ, 2022, Arxiv, DOI arXiv:2112.04491
[8]  
Dai ZH, 2019, Arxiv, DOI arXiv:1901.02860
[9]  
Dauphin YN, 2017, PR MACH LEARN RES, V70
[10]  
De Soham, 2020, ADV NEURAL INFORM PR, V33