从局部到全局的零参考低照度图像增强方法

杨伟; 王帅; 吴佳奇; 陈伟; 田子建

doi:10.7652/xjtuxb202404015

您当前的位置：

首页 >

文章列表页 >

从局部到全局的零参考低照度图像增强方法

—————————————————————— | 更新时间：2025-07-09

- 从局部到全局的零参考低照度图像增强方法
- A Zero-Reference Low-Light Image Enhancement Method from Local to Global
- 西安交通大学学报 2024年58卷第4期页码：158-169
- 作者机构：
  
  1. 中国矿业大学(北京)人工智能学院,北京,100083
  2. 国家矿山安全监察局内蒙古局,呼和浩特,010010
  3. 中国矿业大学计算机科学与技术学院,江苏,徐州,221116
- 作者简介：
  
  : 2023-09-25。作者简介: 杨伟(1995—),女,博士生
  田子建(通信作者),男,教授,博士生导师。基金项目: 国家自然科学基金资助项目(52274160)
- 基金信息：
  
  : 2023-09-25。作者简介: 杨伟(1995—),女,博士生;田子建(通信作者),男,教授,博士生导师。基金项目: 国家自然科学基金资助项目(52274160)
- DOI：10.7652/xjtuxb202404015
  中图分类号： TP391
- 网络首发：2024-04-10，
  
  纸质出版：2024
- 稿件说明：
移动端阅览
杨伟, 王帅, 吴佳奇, 等. 从局部到全局的零参考低照度图像增强方法[J]. 西安交通大学学报, 2024,58(4):158-169.

YANG Wei, WANG Shuai, WU Jiaqi, et al. A Zero-Reference Low-Light Image Enhancement Method from Local to Global[J]. 2024, 58(4): 158-169.
杨伟, 王帅, 吴佳奇, 等. 从局部到全局的零参考低照度图像增强方法[J]. 西安交通大学学报, 2024,58(4):158-169. DOI： 10.7652/xjtuxb202404015.

YANG Wei, WANG Shuai, WU Jiaqi, et al. A Zero-Reference Low-Light Image Enhancement Method from Local to Global[J]. 2024, 58(4): 158-169. DOI： 10.7652/xjtuxb202404015.

摘要

为解决现有的低照度图像增强方法存在的色彩失真、细节损失以及暗区增强不足和亮区增强过度导致低照度图像增强效果不理想的问题

提出了一种从局部到全局的零参考低照度图像增强方法。采用局部照度增强对低照度图像进行像素级增强

改进了自适应光照映射估计函数

提升了照度调整能力

避免了生成大量的迭代参数

提高了模型的推理速度; 采用基于Transformer结构的全局图像调整对局部增强后的图像进行全局调整

解决了亮区照度增强过度的曝光问题和暗区照度增强不足的问题

提升了图像的整体对比度; 优化损失函数

对低照度图像特征和增强图像特征进行相似性约束

提升了目标检测精度。实验结果表明

LOL数据集上的客观指标峰值信噪比和结构相似性达到了20.18 dB和0.80

MIT-Adobe FiveK数据集上达到了23.31 dB和0.87

ExDark数据集上增强后图像的目标检测精度提高了7.6%

有效提升了低照度图像可视化质量和目标检测效果。

Abstract

To address the problem of unsatisfactory low-light image enhancement caused by color distortion

loss of details

insufficient enhancement of dark areas

and excessive enhancement of bright areas in existing low-light image enhancement methods

a zero-reference low-light image enhancement method from local to global is proposed. Initially

the low-illumination image is enhanced at the pixel level through local illumination enhancement

the adaptive light mapping function is improved

and the illumination adjustment ability is enhanced to avoid the generation of massive iterative parameters and improve the inference speed of the model. Subsequently

the global adjustment is performed on the locally enhanced image through Transformer-based global image adjustment to tackle the exposure problem of excessive illumination enhancement in the bright area and insufficient illumination enhancement in the dark area

thereby enhancing the overall contrast of the image. The loss function is optimized to constrain similarities between features of the low-illumination image and those of the enhanced image

thereby improving the target detection accuracy. The experimental results show that the objective metrics peak signal-to-noise ratio and structural similarity can reach 20.18 dB and 0.80 on the LOL dataset

23.31 dB and 0.87 on the MIT-Adobe FiveK dataset

and the target detection accuracy of the enhanced image on the ExDark dataset has increased by 7.6%

thus effectively improving the visualization quality of the low-illumination image and the target detection effect.

关键词

Keywords

references

LIU Jiaying, XU Dejia, YANG Wenhan, et al. Benchmarking low-light image enhancement and beyond [J]. International Journal of Computer Vision, 2021, 129(4): 1153-1184.

LOH Y P, CHAN C S. Getting to know low-light images with the exclusively dark dataset [J]. Computer Vision and Image Understanding, 2019, 178: 30-42.

CHEN Chen, CHEN Qifeng, XU Jia, et al. Learning to see in the dark [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 3291-3300.

IBRAHIM H, PIK KONG N S. Brightness preserving dynamic histogram equalization for image contrast enhancement [J]. IEEE Transactions on Consumer Electronics, 2007, 53(4): 1752-1758.

李天钢, 王素品, 秦辰. 基于信息熵窗的小波低频子带弱目标图像的增强 [J]. 西安交通大学学报, 2006, 40(2): 187-190.

LI Tiangang, WANG Supin, QIN Chen. Enhancement of weak objective image with wavelet low frequency sub-band based on information entropy window [J]. Journal of Xi'an Jiaotong University, 2006, 40(2): 187-190.

LI Mading, LIU Jiaying, YANG Wenhan, et al. Structure-revealing low-light image enhancement via robust Retinex model [J]. IEEE Transactions on Image Processing, 2018, 27(6): 2828-2841.

GU Zhihao, LI Fang, FANG Faming, et al. A novel Retinex-based fractional-order variational model for images with severely low light [J]. IEEE Transactions on Image Processing, 2020, 29: 3239-3253.

LI Lin, WANG Ronggang, WANG Wenmin, et al. A low-light image enhancement method for both denoising and contrast enlarging [C]//2015 IEEE International Conference on Image Processing(ICIP). Piscataway, NJ, USA: IEEE, 2015: 3730-3734.

DONG Xuan, WANG Guan, PANG Yi, et al. Fast efficient algorithm for enhancement of low lighting video [C]//2011 IEEE International Conference on Multimedia and Expo. Piscataway, NJ, USA: IEEE, 2011: 1-6.

WANG Wencheng, WU Xiaojin, YUAN Xiaohui, et al. An experiment-based review of low-light image enhancement methods [J]. IEEE Access, 2020, 8: 87884-87917.

LÜ Feifan, LU Feng, WU Jianhua, et al. MBLLEN: low-light image/video enhancement using CNNs [C]//British Machine Vision Conference 2018. Guildford, UK: BMVA Press, 2018: 20193807460225.

LI Chongyi, GUO Jichang, PORIKLI F, et al. LightenNet: a convolutional neural network for weakly illuminated image enhancement [J]. Pattern Recognition Letters, 2018, 104: 15-22.

YANG Wenhan, WANG Wenjing, HUANG Haofeng, et al. Sparse gradient regularized deep Retinex network for robust low-light image enhancement [J]. IEEE Transactions on Image Processing, 2021, 30: 2072-2086.

WANG Ruixing, ZHANG Qing, FU C W, et al. Underexposed photo enhancement using deep illumination estimation [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2019: 6842-6850.

WEI Chen, WANG Wenjing, YANG Wenhan, et al. Deep Retinex decomposition for low-light enhance-ment [C]//British Machine Vision Conference 2018. Guildford, UK: BMVA Press, 2018: 20193807460275.

ZHANG Yonghua, ZHANG Jiawan, GUO Xiaojie. Kindling the darkness: a practical low-light image enhancer [C]//Proceedings of the 27th ACM International Conference on Multimedia. New York, NY, USA: Association for Computing Machinery, 2019: 1632-1640.

ZHANG Yonghua, GUO Xiaojie, MA Jiayi, et al. Beyond brightening low-light images [J]. International Journal of Computer Vision, 2021, 129(4): 1013-1037.

YU Runsheng, LIU Wenyu, ZHANG Yasen, et al. DeepExposure: learning to expose photos with asynchronously reinforced adversarial learning [C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook, NY, USA: Curran Associates Inc., 2018: 2153-2163.

JIANG Yifan, GONG Xinyu, LIU Ding, et al. EnlightenGAN: deep light enhancement without paired supervision [J]. IEEE Transactions on Image Processing, 2021, 30: 2340-2349.

ZHANG Lin, ZHANG Lijun, LIU Xiao, et al. Zero-shot restoration of back-lit images using deep internal learning [C]//Proceedings of the 27th ACM International Conference on Multimedia. New York, NY, USA: Association for Computing Machinery, 2019: 1623-1631.

GUO Chunle, LI Chongyi, GUO Jichang, et al. Zero-reference deep curve estimation for low-light image enhancement [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2020: 1777-1786.

LI Chongyi, GUO Chunle, LOY C C. Learning to enhance low-light image via zero-reference deep curve estimation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(8): 4225-4238.

DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: transformers for image recognition at scale [C]//ICLR 2021. New York, USA: ICLR, 2021: 3458.

高峰, 汲胜昌, 郭洁, 等. 采用对比学习的多阶段Transformer图像去雾方法 [J]. 西安交通大学学报, 2023, 57(1): 195-210.

GAO Feng, JI Shengchang, GUO Jie, et al. A multi-stage transformer network for image dehazing based on contrastive learning [J]. Journal of Xi'an Jiaotong University, 2023, 57(1): 195-210.

杨瑷玮, 王华珂, 侯兴松. 从全局到局部: 双注意力融合去雾网络 [J]. 西安交通大学学报, 2023, 57(7): 191-200.

YANG Aiwei, WANG Huake, HOU Xingsong. From global to local: a dual-attention fusion dehazing network [J]. Journal of Xi'an Jiaotong University, 2023, 57(7): 191-200.

MERTENS T, KAUTZ J, VAN REETH F. Exposure fusion: a simple and practical alternative to high dynamic range photography [J]. Computer Graphics Forum, 2009, 28(1): 161-171.

甄志龙, 张居晓. 卡方统计中基于KL散度的高维文本数据特征筛选 [J]. 统计与决策, 2022, 38(17): 43-46.

ZHEN Zhilong, ZHANG Juxiao. Feature screening for high dimensional text data based on KL divergence in chi-squared statistics [J]. Statistics Decision, 2022, 38(17): 43-46.

CAI Jianrui, GU Shuhang, ZHANG Lei, et al. Learning a deep single image contrast enhancer from multi-exposure images [J]. IEEE Transactions on Image Processing, 2018, 27(4): 2049-2062.

ZAMIR S W, ARORA A, KHAN S, et al. Learning enriched features for fast image restoration and enhancement [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(2): 1934-1948.

MA Long, MA Tengyu, LIU Risheng, et al. Toward fast, flexible, and robust low-light image enhancement [C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2022: 5627-5636.

BYCHKOVSKY V, PARIS S, CHAN E, et al. Learning photographic global tonal adjustment with a database of input/output image pairs [C]//CVPR 2011. Piscataway, NJ, USA: IEEE, 2011: 97-104.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

深度学习驱动的碳纤维管壁缺陷镜面红外检测无损定量评估方法

复杂天气下铁轨异物入侵目标检测研究

一种轻量级多模态车辆轨迹预测算法

一种Roberts自适应边缘检测方法

人眼视觉特性与粗糙集结合的X射线图像增强算法