DANet: A Domain Alignment Network for Low-Light Image Enhancement

被引:0
|
作者
Li, Qiao [1 ]
Jiang, Bin [1 ]
Bo, Xiaochen [2 ]
Yang, Chao [1 ]
Wu, Xu [3 ]
机构
[1] Hunan Univ, Coll Comp Sci & Elect Engn, Changsha 410082, Peoples R China
[2] Acad Mil Med Sci, Beijing 100850, Peoples R China
[3] Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen 518060, Peoples R China
关键词
low-light image enhancement; multi-domain alignment; convolution-transformer module;
D O I
10.3390/electronics13152954
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We propose restoring low-light images suffering from severe degradation using a deep-learning approach. A significant domain gap exists between low-light and real images, which previous methods have failed to address with domain alignment. To tackle this, we introduce a domain alignment network leveraging dual encoders and a domain alignment loss. Specifically, we train two dual encoders to transform low-light and real images into two latent spaces and align these spaces using a domain alignment loss. Additionally, we design a Convolution-Transformer module (CTM) during the encoding process to comprehensively extract both local and global features. Experimental results on four benchmark datasets demonstrate that our proposed A Domain Alignment Network(DANet) method outperforms state-of-the-art methods.
引用
收藏
页数:15
相关论文
共 50 条
  • [11] Hierarchical guided network for low-light image enhancement
    Feng, Xiaomei
    Li, Jinjiang
    Fan, Hui
    IET IMAGE PROCESSING, 2021, 15 (13) : 3254 - 3266
  • [12] Deep Lightening Network for Low-light Image Enhancement
    Wang, Li-Wen
    Liu, Zhi-Song
    Siu, Wan-Chi
    Lun, Daniel Pak-Kong
    2020 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2020,
  • [13] Invertible network for unpaired low-light image enhancement
    Zhang, Jize
    Wang, Haolin
    Wu, Xiaohe
    Zuo, Wangmeng
    VISUAL COMPUTER, 2024, 40 (01): : 109 - 120
  • [14] Unsupervised Low-Light Image Enhancement in the Fourier Transform Domain
    Ming, Feng
    Wei, Zhihui
    Zhang, Jun
    APPLIED SCIENCES-BASEL, 2024, 14 (01):
  • [15] Luminance domain-guided low-light image enhancement
    Li Y.
    Wang C.
    Liang B.
    Cai F.
    Ding Y.
    Neural Computing and Applications, 2024, 36 (21) : 13187 - 13203
  • [16] DEANet: Decomposition Enhancement and Adjustment Network for Low-Light Image Enhancement
    Jiang, Yonglong
    Li, Liangliang
    Zhu, Jiahe
    Xue, Yuan
    Ma, Hongbing
    TSINGHUA SCIENCE AND TECHNOLOGY, 2023, 28 (04): : 743 - 753
  • [17] A deep Retinex network for underwater low-light image enhancement
    Ji, Kai
    Lei, Weimin
    Zhang, Wei
    MACHINE VISION AND APPLICATIONS, 2023, 34 (06)
  • [18] Deep Pyramid Network for Low-Light Endoscopic Image Enhancement
    Yue, Guanghui
    Gao, Jie
    Cong, Runmin
    Zhou, Tianwei
    Li, Leida
    Wang, Tianfu
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (05) : 3834 - 3845
  • [19] Adaptive lightweight Transformer network for low-light image enhancement
    Meng, De
    Lei, Zhichun
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (6-7) : 5365 - 5375
  • [20] Low-Light Image Enhancement via a Deep Hybrid Network
    Ren, Wenqi
    Liu, Sifei
    Ma, Lin
    Xu, Qianqian
    Xu, Xiangyu
    Cao, Xiaochun
    Du, Junping
    Yang, Ming-Hsuan
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (09) : 4364 - 4375