低光图像增强（Low-light image enhancement）文章整理

低光图像增强是图像增强任务中的重要组成部分，目前对于低光图像增强方法的整理参差不全。因此希望在以有的文章基础上整理汇总一下现有的低光图像增强算法（文章和代码）。希望为自己以及大家查找低光图像增强领域的文章和代码提供一些便捷。

首先介绍一些比较适用的网址，前三个是github上对低光图像增强进行整理的网址，第四个是paperswithcode网站上关于低光图像整理的链接。

常用数据集

LOL : https://daooshee.github.io/BMVC2018website/
Cite as: Wei C, Wang W, Yang W, et al. Deep retinex decomposition for low-light enhancement[J]. arXiv preprint arXiv:1808.04560, 2018.
MEF : https://drive.google.com/drive/folders/1lp6m5JE3kf3M66Dicbx5wSnvhxt90V4T
Cite as: Ma K, Zeng K, Wang Z. Perceptual quality assessment for multi-exposure image fusion[J]. IEEE Transactions on Image Processing, 2015, 24(11): 3345-3356.
SID : https://github.com/cchen156/Learning-to-See-in-the-Dark
Cite as: Chen C, Chen Q, Xu J, et al. Learning to see in the dark[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 3291-3300.
VV : https://drive.google.com/drive/folders/1lp6m5JE3kf3M66Dicbx5wSnvhxt90V4T
DICM : https://drive.google.com/drive/folders/1lp6m5JE3kf3M66Dicbx5wSnvhxt90V4T
Cite as: Lee C, Lee C, Kim C S. Contrast enhancement based on layered difference representation[C]//2012 19th IEEE International Conference on Image Processing. IEEE, 2012: 965-968.
LIME : https://drive.google.com/file/d/0BwVzAzXoqrSXb3prWUV1YzBjZzg/view
Cite as: Guo X, Li Y, Ling H. LIME: Low-light image enhancement via illumination map estimation[J]. IEEE Transactions on image processing, 2016, 26(2): 982-993.
SCIE : https://github.com/csjcai/SICE
Cite as: Cai J, Gu S, Zhang L. Learning a deep single image contrast enhancer from multi-exposure images[J]. IEEE Transactions on Image Processing, 2018, 27(4): 2049-2062.
NPE : https://drive.google.com/drive/folders/1lp6m5JE3kf3M66Dicbx5wSnvhxt90V4T
Cite as: Wang S, Zheng J, Hu H M, et al. Naturalness preserved enhancement algorithm for non-uniform illumination images[J]. IEEE Transactions on Image Processing, 2013, 22(9): 3538-3548.

【2022】

1、文章：DRLIE: Flexible Low-Light Image Enhancement via Disentangled Representations【无监督学习】【用户自定义增强】

Cite as: Tang, Linfeng, et al. “DRLIE: Flexible Low-Light Image Enhancement via Disentangled Representations.” IEEE Transactions on Neural Networks and Learning Systems (2022). .

Paper: https://ieeexplore.ieee.org/abstract/document/9833451/

Code: https://github.com/Linfeng-Tang/DRLIE 【TensorFlow】

【2021】

1、文章：EnlightenGAN: Deep Light Enhancement Without Paired Supervision【半监督学习】【GAN】

Cite as: Y. Jiang et al., “EnlightenGAN: Deep Light Enhancement Without Paired Supervision,” in IEEE Transactions on Image Processing, vol. 30, pp. 2340-2349, 2021, doi: 10.1109/TIP.2021.3051462 .

Paper: https://ieeexplore.ieee.org/abstract/document/9334429

Code: https://github.com/VITA-Group/EnlightenGAN 【Pytorch】

2、文章：Beyond Brightening Low-light Images【监督学习】【Retinex】

Cite as: Zhang Y, Guo X, Ma J, et al. Beyond Brightening Low-light Images[J]. International Journal of Computer Vision, 2021, 129(4): 1013-1037.

Paper: https://link.springer.com/article/10.1007/s11263-020-01407-x

Code: https://github.com/zhangyhuaee/KinD 【Tensorflow】

【2020】

1、文章： Zero-reference deep curve estimation for low-light image enhancement【Zero-short Learning】

Cite as: Guo C, Li C, Guo J, et al. Zero-reference deep curve estimation for low-light image enhancement[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 1780-1789.

Paper: https://openaccess.thecvf.com/content_CVPR_2020/html/Guo_Zero-Reference_Deep_Curve_Estimation_for_Low-Light_Image_Enhancement_CVPR_2020_paper.html

Code: https://github.com/Li-Chongyi/Zero-DCE 【Pytorch】

2、文章：From fidelity to perceptual quality: A semi-supervised approach for low-light image enhancement【半监督学习】

Cite as: Yang W, Wang S, Fang Y, et al. From fidelity to perceptual quality: A semi-supervised approach for low-light image enhancement[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 3063-3072.

Paper: https://openaccess.thecvf.com/content_CVPR_2020/html/Yang_From_Fidelity_to_Perceptual_Quality_A_Semi-Supervised_Approach_for_Low-Light_CVPR_2020_paper.html

Code: https://github.com/flyywh/CVPR-2020-Semi-Low-Light 【Pytorch】

3、文章：From fidelity to perceptual quality: A semi-supervised approach for low-light image enhancement【半监督学习】

Paper: https://openaccess.thecvf.com/content_CVPR_2020/html/Yang_From_Fidelity_to_Perceptual_Quality_A_Semi-Supervised_Approach_for_Low-Light_CVPR_2020_paper.html

Code: https://github.com/flyywh/CVPR-2020-Semi-Low-Light 【Pytorch】

4、文章：Fast enhancement for non-uniform illumination images using light-weight CNNs【监督学习】

Cite as: Lv F, Liu B, Lu F. Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs[C]//Proceedings of the 28th ACM International Conference on Multimedia. 2020: 1450-1458.

Paper: https://dl.acm.org/doi/abs/10.1145/3394171.3413925

Code: 未开源【TensorFlow】

5、文章：Integrating semantic segmentation and retinex model for low light image enhancement【Retinex 】

Cite as: Fan M, Wang W, Yang W, et al. Integrating semantic segmentation and retinex model for low-light image enhancement[C]//Proceedings of the 28th ACM International Conference on Multimedia. 2020: 2317-2325.

Paper: https://dl.acm.org/doi/abs/10.1145/3394171.3413757

Code: 未开源

6、文章：Learning to restore low-light images via decomposition-and-enhancement

Cite as: Xu K, Yang X, Yin B, et al. Learning to restore low-light images via decomposition-and-enhancement[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 2281-2290.

Paper: https://openaccess.thecvf.com/content_CVPR_2020/html/Xu_Learning_to_Restore_Low-Light_Images_via_Decomposition-and-Enhancement_CVPR_2020_paper.html

Code: 未开源【PyTorch】

7、文章：EEMEFN: Low-light image enhancement via edge-enhanced multi-exposure fusion network【Multi-exposure Fusion】

Cite as: Zhu M, Pan P, Chen W, et al. Eemefn: Low-light image enhancement via edge-enhanced multi-exposure fusion network[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(07): 13106-13113.

Paper: https://ojs.aaai.org/index.php/AAAI/article/view/7013

Code: 未开源【Pytorch】

8、文章：Lightening network for low-light image enhancement

Cite as: Wang L W, Liu Z S, Siu W C, et al. Lightening network for low-light image enhancement[J]. IEEE Transactions on Image Processing, 2020, 29: 7984-7996.

Paper: https://ieeexplore.ieee.org/abstract/document/9141197

Code: 未开源【Pytorch】

9、文章：Luminance-aware pyramid network for low-light image enhancement

Cite as: Li J, Li J, Fang F, et al. Luminance-aware Pyramid Network for Low-light Image Enhancement[J]. IEEE Transactions on Multimedia, 2020.

Paper: https://ieeexplore.ieee.org/abstract/document/9186194

Code: 未开源【Pytorch】

10、文章： Low light video enhancement using synthetic data produced with an intermediate domain mapping

Cite as: Triantafyllidou D, Moran S, McDonagh S, et al. Low Light Video Enhancement using Synthetic Data Produced with an Intermediate Domain Mapping[C]//European Conference on Computer Vision. Springer, Cham, 2020: 103-119.

Paper: https://link.springer.com/chapter/10.1007/978-3-030-58601-0_7

Code: 未开源【Tensorflow】

11、文章：TBEFN: A two-branch exposure-fusion network for low-light image enhancement

Cite as: Lu K, Zhang L. TBEFN: A two-branch exposure-fusion network for low-light image enhancement[J]. IEEE Transactions on Multimedia, 2020.

Paper: https://ieeexplore.ieee.org/abstract/document/9261119/

Code: https://github.com/lukun199/TBEFN 【Tensorflow】

12、文章：Zero-shot restoration of underexposed images via robust retinex decomposition 【Zero-short Learning】【Retinex】

Cite as: Zhu A, Zhang L, Shen Y, et al. Zero-shot restoration of underexposed images via robust retinex decomposition[C]//2020 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2020: 1-6.

Paper: https://ieeexplore.ieee.org/abstract/document/9102962/

Code: https://aaaaangel.github.io/RRDNet-Homepage 【Pytorch】

**13、文章：DSLR: Deep stacked laplacian restorer for low-light image enhancement **

Cite as: Lim S, Kim W. DSLR: Deep Stacked Laplacian Restorer for Low-light Image Enhancement[J]. IEEE Transactions on Multimedia, 2020.

Paper: https://ieeexplore.ieee.org/abstract/document/9264763/

Code: https://github.com/SeokjaeLIM/DSLR-release 【Pytorch】

【2019】

1、文章：Seeing motion in the dark

Cite as: Chen C, Chen Q, Do M N, et al. Seeing motion in the dark[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019: 3185-3194.

Paper: https://openaccess.thecvf.com/content_ICCV_2019/html/Chen_Seeing_Motion_in_the_Dark_ICCV_2019_paper.html

Code: https://github.com/cchen156/Seeing-Motion-in-the-Dark 【TensorFlow】

2、文章：Learning to see moving object in the dark

Cite as: Jiang H, Zheng Y. Learning to see moving objects in the dark[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019: 7324-7333.

Paper: https://openaccess.thecvf.com/content_ICCV_2019/html/Jiang_Learning_to_See_Moving_Objects_in_the_Dark_ICCV_2019_paper.html

Code: https://github.com/MichaelHYJiang 【TensorFlow】

3、文章：Underexposed photo enhancement using deep illumination estimation

Cite as: Wang R, Zhang Q, Fu C W, et al. Underexposed photo enhancement using deep illumination estimation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 6849-6857.

Paper: https://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Underexposed_Photo_Enhancement_Using_Deep_Illumination_Estimation_CVPR_2019_paper.html

Code: https://github.com/Jia-Research-Lab/DeepUPE 【TensorFlow】

4、文章：Kindling the darkness: A practical low-light image enhancer 【Retinex】

Cite as: Zhang Y, Zhang J, Guo X. Kindling the darkness: A practical low-light image enhancer[C]//Proceedings of the 27th ACM International Conference on Multimedia. 2019: 1632-1640.

Paper: https://dl.acm.org/doi/abs/10.1145/3343031.3350926

Code: https://github.com/zhangyhuaee/KinD 【TensorFlow】

5、文章：Progressive retinex: Mutually reinforced illumination-noise perception network for low-light image enhancement【Retinex】

Cite as: Wang Y, Cao Y, Zha Z J, et al. Progressive retinex: Mutually reinforced illumination-noise perception network for low-light image enhancement[C]//Proceedings of the 27th ACM International Conference on Multimedia. 2019: 2015-2023.

Paper: https://dl.acm.org/doi/abs/10.1145/3343031.3350983

Code: 未开源【Caffe】

6、文章：Low-light image enhancement via a deep hybrid network

Cite as: Ren W, Liu S, Ma L, et al. Low-light image enhancement via a deep hybrid network[J]. IEEE Transactions on Image Processing, 2019, 28(9): 4364-4375.

Paper: https://ieeexplore.ieee.org/abstract/document/8692732/

Code: 未开源【Caffe】

7、文章：Zero-shot restoration of back-lit images using deep internal learning

Cite as: Zhang L, Zhang L, Liu X, et al. Zero-shot restoration of back-lit images using deep internal learning[C]//Proceedings of the 27th ACM International Conference on Multimedia. 2019: 1623-1631.

Paper: https://dl.acm.org/doi/abs/10.1145/3343031.3351069

Code: https://cslinzhang.github.io/ExCNet/ 【PyTorch】

【2018】

1、文章：LightenNet: A convolutional neural network for weakly illuminated image enhancement

Cite as: Li C, Guo J, Porikli F, et al. LightenNet: A convolutional neural network for weakly illuminated image enhancement[J]. Pattern Recognition Letters, 2018, 104: 15-22.

Paper: https://www.sciencedirect.com/science/article/abs/pii/S0167865518300163

Code: https://li-chongyi.github.io/proj_lowlight.html 【Caffe & MATLAB】

2、文章：Deep retinex decomposition for low-light enhancement 【Retinex】

Cite as: Wei C, Wang W, Yang W, et al. Deep retinex decomposition for low-light enhancement[J]. arXiv preprint arXiv:1808.04560, 2018.

Paper: https://arxiv.org/abs/1808.04560

Code: https://github.com/weichen582/RetinexNet 【TensorFlow】

3、文章：MBLLEN: Low-light image/video enhancement using CNNs

Cite as: Lv F, Lu F, Wu J, et al. MBLLEN: Low-Light Image/Video Enhancement Using CNNs[C]//BMVC. 2018: 220.

Paper: http://bmvc2018.org/contents/papers/0700.pdf

Code: https://github.com/Lvfeifan/MBLLEN 【TensorFlow】

4、文章：Learning a deep single image contrast enhancer from multi-exposure images

Cite as: Cai J, Gu S, Zhang L. Learning a deep single image contrast enhancer from multi-exposure images[J]. IEEE Transactions on Image Processing, 2018, 27(4): 2049-2062.

Paper: https://ieeexplore.ieee.org/abstract/document/8259342/

Code: https://github.com/csjcai/SICE 【Caffe & MATLAB】

5、文章：Learning to see in the dark

Cite as: Chen C, Chen Q, Xu J, et al. Learning to see in the dark[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 3291-3300.

Paper: https://openaccess.thecvf.com/content_cvpr_2018/html/Chen_Learning_to_See_CVPR_2018_paper.html

Code: https://github.com/cchen156/Learning-to-See-in-the-Dark 【TensorFlow】

6、文章：DeepExposure: Learning to expose photos with asynchronously reinforced adversarial learning

Cite as: Yu R, Liu W, Zhang Y, et al. Deepexposure: Learning to expose photos with asynchronously reinforced adversarial learning[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018: 2153-2163.

Paper: https://dl.acm.org/doi/abs/10.5555/3326943.3327142

Code: 未开源【TensorFlow】

【2017】

1、文章：LLNet: A deep autoencoder approach to natural low-light image enhancement

Cite as: Lore K G, Akintayo A, Sarkar S. LLNet: A deep autoencoder approach to natural low-light image enhancement[J]. Pattern Recognition, 2017, 61: 650-662.

Paper: https://www.sciencedirect.com/science/article/abs/pii/S003132031630125X

Code: https://github.com/kglore/llnet_color 【Theano】

===================== 分 ========== 割 ========== 线 =====================
由于笔者水平有限，某些最新的论文未被收集整理，欢迎大家讨论交流！

如有疑问可添加笔者扣扣：2458707789@qq.com；备注姓名+学校

稳健曝光校正的双光照估计 [] LIME：通过照明图估计进行低光 图像增强 [] 这两种方法都基于 retinex 建模，旨在通过保留图像的突出结构来估计光照图，同时去除多余的纹理细节。为此，两篇论文都使用了相同的优化公式（参见参考资料）。与第二篇论文（以下称为 LIME）相比，第一篇论文（以下称为 DUAL）引入的新颖性在于对原始图像及其倒置版本的该映射的估计，它允许校正曝光不足和过度曝光图像的暴露部分。此存储库中实现的代码允许使用这两种方法，可以从脚本参数中轻松选择。这个实现在python>=3.7上运行，使用pip安装依赖： pip3 install -r requirements.txt 使用demo.py脚本来增强您的图像。 usage: demo.py 以下文字为博主翻译并添加了自己的理解，斜体为博主自己的想法，若有出错请指出。暗光 图像增强 需要同时有效地处理颜色、亮度、对比度、伪影和噪声等多种因素。本文提出了一种新颖的注意力引导增强方案，并在此基础上构建了端到端多分支（multi-branches） CNN。该方法的关键是计算两个注意力图来分别指导曝光增强和去噪任务。第一个注意力图区分曝光不足的区域和光照较好的区域，而第二个注意力图区分... 虽然目前成像探测技术已经由低空间分辨率向高空间分辨率，由低光谱分辨率到高光谱分辨率发展，但是对于光谱细分成像而言，高空间分辨率和高光谱分辨率往往是矛盾的。然而，受成像机理和成像设备的限制，空间分辨率、光谱带宽、幅宽、信噪比等指标不可避免的需要互相折中，难以直接获取高空间分辨率的高光谱图像。此外，由于载荷平台颤振，成像光学系统调制传递函数引起的模糊降质、系统噪声、大气辐射和云层覆盖效应等，高光谱图像辐射信息质量下降、空间分辨率低、混合像元严重等现象，成为高光谱图像分析、理解和模式识别应用的突出问题。零参考深曲线估计的Pytorch实施以实现低光 图像增强 （）。使用活页夹访问笔记本：在Wandb上找到培训日志： ://wandb.ai/19soumik-rakshit96/zero-dce 嘈杂结果示例 @article{2001.06826, Author = {Chunle Guo and Chongyi Li and Jichang Guo and Chen Change Loy and Junhui Hou and Sam Kwong and Runmin Cong}, Title = {Zero-Reference Deep Curve Estimation for Low - Light Image Enhancement }, Year = {2020}, Eprint = {arXiv:2001 Resources for Low Light Image Enhancement https://github.com/dawnlh/ low - light - image - enhancement -resources ------------------------------------------------------------- Paper TIP 2021 Sparse Gradient Regularized Deep Retinex Network for Robust Low -Ligh 【题目】：URetinex-Net: Retinex-based Deep Unfolding Network for Low - light Image Enhancement 提出了一种基于Retinex的 deep unfolding network （URetinex-Net），它将一个优化问题展开为一个可学习的网络，以将低光图像分解为反射层和光照层。通过将分解问题公式化为隐式先验正则化模型，精心设计了三个基于学习的模块，分别负责数据相关的初始化、高效的展开优化和用户指定的光照增强。现有的低照度 图像增强 技术大多不仅难以处理视觉质量和计算效率，而且在未知的复杂场景中普遍无效。在本文中，我们开发了一个新的自我校准光照（SCI）学习框架，用于在现实世界的低光照场景中快速、灵活和稳健地提高图像亮度。具体来说，我们建立了一个具有权重共享的级联照度学习过程来处理这项任务。考虑到级联模式的计算负担，我们构建了自校准模块，实现了每个阶段的结果之间的收敛，产生了只使用单一基本块进行推理的收益（但在以前的工作中没有利用），这大大降低了计算成本。...... 2. pretrained里边是预训练权重，model_1是欠曝光恢复，model_2是过曝光恢复 3. 在demo里边设置好权重参数路径 4. 在data数据集下input放入需要恢复的图像，运行demo后会在result里生成结果 5. 如果没有gpu环境也可以在cpu里运行，设置use_CUDA参数为False即可 6. 有预训练权重，适合展示恢复效果不关注具体网络实现的情况 CAIP2017的“使用曝光融合框架的新图像对比度增强算法”的Python实现 “通过通道划分增强内容感知的暗图像”的非官方实现。实施“基于retinex的单个水下 图像增强 方法” Matlab代码，“使用对比度增强功能对对比度失真的图像进行无参考质量评估” 加快自适应对比度增强（SUACE）；一种基于OpenCV对比度增强技术。基于局部边缘保留滤镜的2016 HDR红外图像细节增强的matlab代码使用波长补偿和去雾的水下 图像增强 “用于实时 图像增强 的深度双边学习”的实现全卷积网络的快速图像处理 “使用重影提示去除反射”的实施在CUDA上实现的除雾算法。 MATLAB实现的“非局部图像去雾”论文实施“在充满挑战的照明条件下进行视频增强的高效集成算法”。实施“通过融合视频演示增强水下图像和视频” 密集连接的金字塔除雾网络高影响力和最先进的SR方法的集合