[1]WANG Dewen,HU Wangsheng,ZHANG Runlei,et al.Low light image enhancement based on high and low frequency feature fusion[J].CAAI Transactions on Intelligent Systems,2025,20(3):641-648.[doi:10.11992/tis.202405026]
Copy

Low light image enhancement based on high and low frequency feature fusion

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 20 Number of periods: 2025 3 Page number: 641-648 Column: 学术论文—机器感知与模式识别 Public date: 2025-05-05
Title:
Low light image enhancement based on high and low frequency feature fusion
Author(s):
WANG Dewen1; 2;  HU Wangsheng1;  ZHANG Runlei1;  ZHAO Wenqing1; 3
1. Department of Computer, North China Electric Power University, Baoding 071003, China;
2. Hebei Key Laboratory of Knowledge Computing for Energy & Power, Baoding 071003, China;
3. Engineering Research Center of the Intelligent Computing for Complex Energy System, Ministry of Education, Baoding 071003, China
Keywords:
low light; image enhancement; high frequency feature; low frequency feature; feature fusion; attention; multi-scale; residual net; dense connection
CLC:
TP391.41
DOI:
10.11992/tis.202405026
Abstract:
To address the imbalance between performance and cost in existing low light image enhancement, a low light image enhancement method is proposed based on high and low frequency feature fusion. By integrating multi-scale data, this fusion combines geometrically rich low frequency features with semantically rich high frequency features to obtain enhanced images, thereby reducing cost while guaranteeing good image quality. To enhance the feature extraction ability in a low light environment, the residual mix-attention module is designed to focus more on important local regions from the pixel and channel perspectives. To address the information loss due to downsampling, the feature merging module is used to supplement the features after downsampling. Additionally, a multi-residual dense block module is designed to strengthen the feature-reuse capability. Furthermore, the see-in-the-dark dataset was subjected to experiments. Overall, this method achieved peak signal-to-noise ratio and structural similarity of 29.67 and 0.792, respectively, with only 1.5×106 parameters.
References:
[1] 许皓, 钱宇华, 王克琪, 等. 高低频通道特征交叉融合的低光人脸检测算法[J]. 智能系统学报, 2024, 19(2): 472-481.
XU Hao, QIAN Yuhua, WANG Keqi, et al. Low-light face detection method based on the cross fusion of high-and low-frequency channel features[J]. CAAI transactions on intelligent systems, 2024, 19(2): 472-481.
[2] 马龙, 马腾宇, 刘日升. 低光照图像增强算法综述[J]. 中国图象图形学报, 2022, 27(5): 1392-1409.
MA Long, MA Tengyu, LIU Risheng. The review of low-light image enhancement[J]. Journal of image and graphics, 2022, 27(5): 1392-1409.
[3] COLTUC Dinu, BOLON Philippe, CHASSERY J M. Exact histogram specification[J]. IEEE transactions on image processing, 2006, 15(5): 1143-1152.
[4] ARICI T, DIKBAS S, ALTUNBASAK Y. A histogram modification framework and its application for image contrast enhancement[J]. IEEE transactions on image processing, 2009, 18(9): 1921-1935.
[5] 杨先凤, 蒋欣岑, 杜晶晶. 融合伽马变换及分数阶的低照度图像增强算法[J]. 计算机工程与设计, 2021, 42(3): 762-769.
YANG Xianfeng, JIANG Xincen, DU Jingjing. Low illumination image enhancement algorithm based on gamma transformation and fractional order[J]. Computer engineering and design, 2021, 42(3): 762-769.
[6] FU Xueyang, ZENG Delu, HUANG Yue, et al. A weighted variational model for simultaneous reflectance and illumination estimation[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 2782-2790.
[7] 涂清华, 戴声奎. 基于域滤波的自适应Retinex图像增强[J]. 计算机工程与科学, 2016, 38(9): 1830-1835.
XU Qinghua, DAI Shengkui. Adaptive Retinex image enhancement based on domain transform filter[J]. Computer engineering and science, 2016, 38(9): 1830-1835.
[8] 欧嘉敏, 胡晓, 杨佳信. 改进Retinex-Net的低光照图像增强算法[J]. 模式识别与人工智能, 2021, 34(1): 77-86.
OU Jiamin, HU Xiao, YANG Jiaxin. Low-light image enhancement algorithm based on improved Retinex-Net[J]. Pattern recognition and artificial intelligence, 2021, 34(1): 77-86.
[9] GUO Xiaojie, LI Yu, LING Haibin. Lime: low-light image enhancement via illumination map estimation[J]. IEEE transactions on image processing, 2017, 26(2): 982-993.
[10] 赵明华, 汶怡春, 都双丽, 等. 基于照度与场景纹理注意力图的低光图像增强[J]. 中国图象图形学报, 2024, 29(4): 862-874.
ZHAO Minghua, WEN Yichun, DU Shuangli, et al. Low-light image enhancement algorithm based on illumination and scene texture attention map[J]. Journal of image and graphics, 2024, 29(4): 862-876.
[11] GUO Chunle, LI Chongyi, GUO Jichang, et al. Zero-reference deep curve estimation for low-light image enhancement[C]//2020 IEEE Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 1777-1786.
[12] 江泽涛, 覃露露, 秦嘉奇, 等. 一种基于MDARNet的低照度图像增强方法[J]. 软件学报, 2021, 32(12): 3977-3991.
JIANG Zetao, QIN Lulu, QIN Jiaqi, et al. Low-light image enhancement method based on MDARNet[J]. Journal of software, 2021, 32(12): 3977-3991.
[13] 谌贵辉, 林瑾瑜, 李跃华, 等. 注意力机制下的多阶段低照度图像增强网络[J]. 计算机应用, 2023, 43(2): 552-559.
CHEN Guihui, LIN Jinyu, LI Yuehua, et al. Multi-stage low-illuminance image enhancement network based on attention mechanism[J]. Journal of computer application, 2023, 43(2): 552-559.
[14] YANG Wenhan, WANG Shiqi, FANG Yuming, et al. From fidelity to perceptual quality: a semi-supervised approach for low-light image enhancement[C]//2020 IEEE Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 3060-3069.
[15] XU Ke, YANG Xin, YIN Baocai, et al. Learning to restore low-light images via decomposition and enhancement[C]//2020 IEEE Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 2278-2287.
[16] LAMBA M, MITRA K. Restoring extremely dark images in real time[C]//2020 IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2021: 3486-3496.
[17] ATOUM Y, YE Mao, REN Liu, et al. Color-wise attention network for low-light image enhancement[C]//2020 IEEE Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 2130-2139.
[18] ZHU Minfeng, PAN Pingbo, CHEN Wei, et al. EEMEFN: Low-light image enhancement via edge-enhanced multi-exposure fusion network[C]//AAAI conference on artificial intelligence. New York: AAAI, 2020: 13106-13113.
[19] 杨勇, 刘惠义. 极端低光情况下的图像增强方法[J]. 图学学报, 2020, 41(4): 520-528.
YANG Yong, LIU Huiyi. The method of image enhancement under extremely low-light conditions[J]. Journal of graphics, 2020, 41(4): 520-528.
[20] WANG Y, HUANG H, XU Q, et al. Practical deep raw image denoising on mobile devices[C]//2020 European Conference Computer Vision. Glasgow: ECCV, 2020: 12351.
[21] ZAMIR S W, ARORA A, KHAN S. Multi-stage progressive image restoration[C]// 2021 IEEE Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 14816-14826.
[22] ZOU Yunhao, FU Ying. Estimating fine-grained noise model via contrastive learning[C]//2022 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 12672-12681.
[23] CHEN Chen, CHEN Qifeng, XU Jia, et al. Learning to see in the dark. [C]//2018 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 3291-3300.
[24] WANG Y, ZHU X, ZHAO Y, et al. Enhancement of low-light image based on wavelet U-Net[J]. Journal of physics, 2019, 1345(2): 022030.
[25] MAHARJAN P, LI Li, ZHU Li, et al. Improving extreme low-light image denoising via residual learning[C]//2019 IEEE International Conference on Multimedia and Expo. Shanghai: IEEE, 2019: 916-921.
[26] LAMBA M, BALAJI A, MITRA K. Towards fast and light-weight restoration of dark images [EB/OL]. (2020-11-28) [2024-04-20]. https://doi.org/10.48550/arXiv.2011.14133.
[27] GU Shuhang, LI Yawei, VAN LUC Gool, et al. Self-guided network for fast image denoising[C]//2019 IEEE International Conference on Computer Vision. Seoul: IEEE, 2019: 2511-2520.
[28] DONG Xingbo, XU Wanyan, MIAO Zhihui. et al. Abandoning the bayer-filter to see in the dark[C]//2022 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 17410-17419.
[29] JIN Xin, HAN Linghao, LI Zhen, et al. DNF: decouple and feedback network for seeing in the dark[C]//2023 IEEE Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023: 18135-18144.
[30] REN Wenqi, LIU Sifei, MA Lin, et al. Lowlight image enhancement via a deep hybrid network[J]. IEEE transactions on image processing, 2019, 28(9): 4364-4375.
[31] ZHANG Yulun, TIAN Yapeng, KONG Yu. Residual dense network for image super-resolution[J]. IEEE transactions on image processing, 2022, 22: 1391-1405.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems