Skip to content

Latest commit

 

History

History
372 lines (289 loc) · 33 KB

ImageEnhancement.md

File metadata and controls

372 lines (289 loc) · 33 KB
Raw

Table of Contents

Image Enhancement

  • CLIPtone: Unsupervised Learning for Text-based Image Tone Adjustment
    Hyeongmin Lee, Kyoungkook Kang, Jungseul Ok, Sunghyun Cho
    [CVPR 2024] [PyTorch-Code]

  • Iterative Prompt Learning for Unsupervised Backlit Image Enhancement
    Zhexin Liang,  Chongyi Li, Shangchen Zhou,  Ruicheng Feng,  Chen Change Loy
    [ICCV 2023 Oral] [Project] [PyTorch-Code]
    [CLIP-LIT] [★★]

  • Controllable Image Enhancement
    Heewon Kim, Kyoung Mu Lee
    [arXiv 2206]

  • You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction
    Ziteng Cui, Kunchang Li, Lin Gu, Shenghan Su, Peng Gao, Zhengkai Jiang, Yu Qiao, Tatsuya Harada
    [BMVC 2022] [PyTorch-Code]

  • CLUT-Net: Learning Adaptively Compressed Representations of 3DLUTs for Lightweight Image Enhancement
    Fengyi Zhang, Hui Zeng, Tianjun Zhang, Lin Zhang
    [MM 2022] [PyTorch-Code]

  • Neural Color Operators for Sequential Image Retouching
    Yili Wang, Xin Li, [Kun Xu], Dongliang He, Qi Zhang, Fu Li, Errui Ding
    [ECCV 2022] [PyTorch-Code]
    [★★] 用lightroom的3个算子生成gt, 训练独立的色彩模块. 再用一个轻量级强度预测网络控制几个字模块的增强幅度.

  • SepLUT: Separable Lookup Tables for Real-time Image Enhancement
    Canqian Yang, Meiguang Jin, Yi Xu, Rui Zhang, Ying Chen, Huaida Liu
    [ECCV 2022] [PyTorch-Code]
    [★☆] 3个1d lut + 3d lut

  • Exposure Correction Model to Enhance Image Quality
    Fevziye Irem Eyiokur, Dogucan Yaman, Hazım Kemal Ekenel, Alexander Waibel
    [CVPRW 2022] [PyTorch-Code]

  • AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement
    Canqian Yang, Meiguang Jin, Xu Jia, Yi Xu, Ying Chen
    [CVPR 2022] [PyTorch-Code]
    [★★] 可学习的3dlut网格间距

  • STAR: A Structure-Aware Lightweight Transformer for Real-time Image Enhancement
    [Author] Zhaoyang Zhang, Yitong Jiang, Jun Jiang, Xiaogang Wang, Ping Luo, Jinwei Gu
    [ICCV 2021]

  • Learning Multi-Scale Photo Exposure Correction
    Mahmoud Afifi, Konstantinos G. Derpanis, Björn Ommer, Michael S. Brown
    [CVPR 2021] [PyTorch-Code]
    [★☆] coarse-to-fine增强的策略, 并在每个level加入相应的拉普拉斯金字塔层作为细节信息. 使用L1和GAN loss. 效果不错.

  • DeepLPF: Deep Local Parametric Filters for Image Enhancement
    Sean Moran, Pierre Marza, Steven McDonagh, Sarah Parisot, Gregory Slabaugh
    [CVPR 2020] [PyTorch-Code]
    [★★] 华为欧洲实验室. 把lightroom等修图软件中的brush, graduated filters, radial filters工具用CNN模拟出来. 1) 用一unet做增强并提取feature; 2) 预测polynomial filter参数(即brush)并做增强; 3) 分别预测graduated和radial filter参数并计算mask; 4) 渐变/径向分支mask对polynomial增强参数做加权, 与初步增强结果做加权融合.

  • Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time
    Hui Zeng, Jianrui Cai, Lida Li, Zisheng Cao, Lei Zhang
    [TPAMI 2020] [Code]
    [★★] 预测若干个3D LUT, 并用一个轻量级CNN预测每个LUT的权重. LUT和CNN同时训练, 采用了平滑和单调两种正则方式消除伪影等问题. 非常适合处理大图, 实际应用价值大, 值得一试.

  • Global and Local Enhancement Networks for Paired and Unpaired Image Enhancement
    Han-Ul Kim, Young Jun Koh, Chang-Su Kim
    [ECCV 2020] [Project] [Pytorch-Code]
    [GLeNet] [★★] (曲线预测) 全局预测曲线(3*256) + 局部增强. 无监督训练部分采用类似cycle gan的策略. 更具有实用性的曲线预测策略已经开始获得关注, 相关论文越来越多了.

  • PieNet: Personalized Image Enhancement Network
    Han-Ul Kim, Young Jun Koh, Chang-Su Kim
    [ECCV 2020] [Project] [TF-Code]
    [★★] (个性化增强) 使用度量学习的方法, 学习一个网络, 从用户选择的若干图像中提取偏好特征向量, 该特征向量作用在增强网络上, 产生符合用户喜好的增强结果.

  • Conditional Sequential Modulation for Efficient Global Image Retouching
    Jingwen He, Yihao Liu, Yu Qiao, Chao Dong
    [ECCV 2020] [Pytorch-Code]
    [CSRNet] [★] (控制restoration level) 本文聚焦于全局retouching, 认为很多操作都可以用MLP模拟, 据此设计了一个由若干1x1卷积组成的base网络, 另外又设计了一个condition网络提取全局信息对base网络各层进行调制.

  • Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images
    Qunliang Xing, Mai Xu, Tianyi Li, Zhenyu Guan
    [ECCV 2020] [Pytorch-Code]
    [RBQE] [☆] 提出一个simple to hard的图像增强算法, 通过一个质量评估模块判断当前增强结果是否符合要求, 若符合要求, 就提前推出. 本文主要关注压缩图像, 不知是否可扩展到超分等任务中

  • URIE: Universal Image Enhancement for Visual Recognition in the Wild
    Taeyoung Son, Juwon Kang, Namyup Kim, Sunghyun Cho, Suha Kwak
    [ECCV 2020] [Project] [Pytorch-Code]
    [★] 提出了一个通用的质量增强模块, 可插入到检测分割等识别任务之前, 提升这些任务的性能.

  • CURL: Neural Curve Layers for Global Image Enhancement
    Sean Moran, Steven McDonagh, Gregory Slabaugh
    [ICLR 2020] [Pytorch-Code]
    [★] 在LAB, RGB, HSV三个空间预测curve

  • Content-preserving Tone Adjustment for Image Enhancement
    Simone Bianco, Claudio Cusano, Flavio Piccoli, Raimondo Schettini
    [CVPRW 2019] [PyTorch-Code]
    [★☆] 有点类似HRDNet, 在小分辨率预测输入值的分段映射系数, 在原图上增强. 速度快, 应该有较强的实用性.

  • Aesthetic-Driven Image Enhancement by Adversarial Learning
    Yubin Deng, Chen Change Loy, Xiaoou Tang
    [MM 2018] [Project] [Torch-Code]
    [EnhanceGAN] [★] weakly supervised方法, 学习crop和色彩变换参数, 增强aesthetic quality

  • Perception-Preserving Convolutional Networks for Image Enhancement on Smartphones
    Zheng Hui, Xiumei Wang, Lirui Deng, Xinbo Gao
    [ECCVW 2018] [TF-Code]
    [PPCN] [☆] ECCV PIRM(Perceptual Image Restoration and Manipulation ) 2018竞赛, 一个快速图像增强方案

  • Fast and Efficient Image Quality Enhancement via Desubpixel Convolutional Neural Networks
    Thang Vu, Cao V. Nguyen, Trung X. Pham, Tung M. Luu, and Chang D. Yoo
    [ECCVW 2018] [TF-Code]
    [FEQE] [☆] 使用pixel shuffle的实时图像增强网络

  • WESPE: Weakly Supervised Photo Enhancer for Digital Cameras
    Andrey Ignatov, Nikolay Kobyshev, Radu Timofte , Kenneth Vanhoey, Luc Van Gool
    [CVPRW 2018] [Project]
    [★]

  • Range Scaling Global U-Net for Perceptual Image Enhancement on Mobile Devices
    Jie Huang, Pengfei Zhu, Mingrui Geng, Jiewen Ran, Xingguang Zhou, Chen Xing, Pengfei Wan, Xiangyang Ji
    [ECCVW 2018] [TF-Code]
    [RSGUNet] [★] UNet + Global Pooling feature + 输入输出feature间的elementwise scaling

  • DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks
    Andrey Ignatov, Nikolay Kobyshev, Kenneth Vanhoey, Radu Timofte , Luc Van Gool
    [ICCV 2017] [Code]
    [DPED] [★★] 1) 从变换的角度出发, 学习一个从低质量图像到高质量图片的变换函数. 2) 变换部分采用残差快结构的CNN，定义了4个loss (color, texture, content, variance). color loss是图像进行高斯模糊后的均方差, texture loss是adversarial loss, content loss是perceptual loss, variance loss是图像梯度的模.3) 提出了用于图像质量增强的数据集DPED, 包括iPhone, BlackBerry和Sony三种手机与Canon单反相机的图相对.

  • Deep Bilateral Learning for Real-Time Image Enhancement
    Michaël Gharbi, Jiawen Chen, Jonathan T. Barron, Samuel W. Hasinoff, Frédo Durand
    [Siggraph 2017] [Project]
    [HDRNet] [★★★] 1) 提出了一个实时图像增强网络, 速度快, 效果好. 2) 网络分为两个分支, 低分辨率分支提取特征, 学习每个像素的色彩映射参数; 高分辨率分支负责提取和保留细节信息. low res分支学到的映射参数通过类似于双线性差值的过程上采样到high res, 最后对high res图像做色彩映射并输出. 3) 学习映射参数部分, 采用bilateral grid的思路. 第三个维度被解释成8*12的网格, 意思是对8个灰度level做不同的色彩映射. 处理时选择哪个level的参数, 由high res分支生成的引导图决定.

Low-light Image Enhancement

  • LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models
    Hai Jiang, Ao Luo, Xiaohong Liu, Songchen Han, Shuaicheng Liu
    [ECCV 2024] [PyTorch-Code]
    [★☆] 无监督亮度增强. 训练时, 给定非配对的亮度/暗图, 提取反射图和光照图feature, 生成diffusion模型的x0, 注入暗图反射feature, 并设计了一系列loss, 约束反射, 亮度feature

  • Low-light Image Enhancement with Wavelet-based Diffusion Models
    Hai Jiang, Ao Luo, Songchen Han, Haoqiang Fan, Shuaicheng Liu
    [Siggraph Asia 2023] [PyTorch-Code]
    [★☆] Harr小波分解, 在平均分亮上做亮度增强. 以low图做diffusion模型的条件输入

  • Brighten-and-Colorize: A Decoupled Network for Customized Low-Light Image Enhancement
    Chenxi Wang, Zhi Jin
    [MM 2023] [PyTorch-Code]
    [BCNet] [★] 亮度颜色解耦, 用户可以输入参考图片指导输出的色调, 并有一个可调参数控制饱和度

  • Implicit Neural Representation for Cooperative Low-light Image Enhancement
    Shuzhou Yang, Moxuan Ding, Yanmin Wu, Zihan Li, Jian Zhang
    [ICCV 2023] [PyTorch-Code]
    [NeRCo]

  • ExposureDiffusion: Learning to Expose for Low-light Image Enhancement
    Yufei Wang, Yi Yu, Wenhan Yang, Lanqing Guo, Lap-Pui Chau, Alex C. Kot, Bihan Wen
    [ICCV 2023] [PyTorch-Code]

  • Empowering Low-Light Image Enhancer through Customized Learnable Priors
    Naishan Zheng, Man Zhou, Yanmeng Dong, Xiangyu Rui, Jie Huang, Chongyi Li, Feng Zhao
    [ICCV 2023] [PyTorch-Code]

  • Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement
    Yuanhao Cai, Hao Bian, Jing Lin, Haoqian Wang, Radu Timofte, Yulun Zhang
    [ICCV 2023] [PyTorch-Code]

  • DNF: Decouple and Feedback Network for Seeing in the Dark
    Xin Jin, Ling-Hao Han, Zhen Li, Chun-Le Guo, Zhi Chai, Chongyi Li
    [CVPR 2023] [PyTorch-Code]

  • Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement
    Yuhui Wu, Chen Pan, Guoqing Wang, Yang Yang, Jiwei Wei, Chongyi Li, Heng Tao Shen
    [CVPR 2023] [PyTorch-Code]

  • You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction
    Ziteng Cui, Kunchang Li, Lin Gu, Shenghan Su, Peng Gao, Zhengkai Jiang, Yu Qiao, Tatsuya Harada
    [arXiv 2205] [PyTorch-Code]

  • URetinex-Net: Retinex-based Deep Unfolding Network for Low-light-Image-Enhancement
    Wenhui Wu, Jian Weng, Pingping Zhang, Xu Wang, Wenhan Yang, Jianmin Jiang
    [CVPR 2022] [PyTorch-Code]

  • SNR-Aware Low-Light Image Enhancement
    Xiaogang Xu, Ruixing Wang, Chi-Wing Fu, Jiaya Jia
    [CVPR 2022] [PyTorch-Code]

  • Deep Color Consistent Network for Low-Light Image Enhancement
    Zhao Zhang, Huan Zheng, Richang Hong, Mingliang Xu, Shuicheng Yan, Meng Wang
    [CVPR 2022]

  • Toward Fast, Flexible, and Robust Low-Light Image Enhancement
    Long Ma, Tengyu Ma, Risheng Liu, Xin Fan, Zhongxuan Luo
    [CVPR 2022 Oral] [Pytorch-Code]

  • Low-Light Image Enhancement with Normalizing Flow
    Yufei Wang, Renjie Wan, Wenhan Yang, Haoliang Li, Lap-pui Chau, Alex C. Kot
    [AAAI 2022 Oral] [Project] [Pytorch-Code]
    [LLFLOW]

  • StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement
    Yuda Song, Hui Qian, Xin Du
    [ICCV 2021] [Pytorch-Code]
    [★★] 预先学习一个style特征提取网络, 通过dual adain将style注入增强网络, 实现风格可控的增强. 增强网络为基于rgbxy的曲线预测网络

  • Restoring Extremely Dark Images in Real Time
    Mohit Lamba, Kaushik Mitra
    [CVPR 2021] [Pytorch-Code]
    [★☆] 轻量化暗光增强. 多尺度网络并行处理, 改进了RDB block, 对输入先做自适应的放大再送入网络.

  • Low-light Image and Video Enhancement Using Deep Learning: A Survey
    Chongyi Li, Chunle Guo, Linghao Han, Jun Jiang, Ming-Ming Cheng, Jinwei Gu, Chen Change Loy
    [TPAMI 2021] [Project]

  • Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement
    Chunle Guo, Chongyi Li, Jichang Guo, Chen Change Loy, Junhui Hou, Sam Kwong, Runmin Cong
    [CVPR 2020] [Project] [Pytorch-Code] [TF-Code]
    [Zero-DCE] [★★] 1) 一篇挺有趣的论文, 把tone mapping看成pixel-wise的曲线预测问题, 设计了一个小型曲线估计网络, 并提出了几个无监督loss, 得到了不错的结果. 2) 一些局限性: 提出的一系列约束loss对于增强部分区域可能不太适用, 比如对夜景图片增强前景的同时保持夜空是暗的

  • Learning to Restore Low-Light Images via Decomposition-and-Enhancement
    Ke Xu, Xin Yang, Baocai Yin, Rynson W.H. Lau
    [CVPR 2020]
    [★] 在亮度增强的同时考虑去噪. 认为低频部分受噪声影响小(???)所以容易在低频部分进行增强. 低频部分增强后通过一个网络学习恢复高频部分. 设计了两个模块用于提取低频信息和扩大感受野.

  • From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement
    Wenhan Yang, Shiqi Wang, Yuming Fang, Yue Wang, Jiaying Liu
    [CVPR 2020] [Pytorch-Code]
    [DRBN] [☆] 分为有监督部分和无监督(GAN)两部分. 结构比较繁琐.

  • EEMEFN: Low-Light Image Enhancement via Edge-Enhanced Multi-Exposure Fusion Network
    Minfeng Zhu, Pingbo Pan, Wei Chen, Yi Yang
    [AAAI 2020]
    [★] 大致浏览. 输入为raw, 设计了一个多分支网络, 分别处理不同曝光值得输入并将结果融合, 里面的参考曝光值不知道是怎么得到的. 另外还加入一个边缘增强网络, 方法是现成的.

  • Self-supervised Image Enhancement Network: Training With Low Light Images Only
    Yu Zhang, Xiaoguang Di, Bin Zhang, Chunhui Wang
    [arXiv 2002] [TF-Code]

  • Unsupervised Real-world Low-light Image Enhancement with Decoupled Networks
    Wei Xiong, Ding Liu, Xiaohui Shen, Chen Fang, Jiebo Luo
    [arXiv 2005]
    [★] 无监督做亮度增强和去噪. 分为亮度增强和去噪两阶段, 亮度采用Retinex思想, 使用global和local的GAN做loss. 去噪部分提出构建Pseudo Triples的方法, 结合GAN去噪.

  • Deep Bilateral Retinex for Low-Light Image Enhancement
    Jinxiu Liang, Yong Xu, Yuhui Quan, Jingwen Wang, Haibin Ling, Hui Ji
    [arXiv 2007]

  • Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs
    Feifan Lv, Bo Liu, Feng Lu
    [MM 2020]
    [★★] 1) 超轻量级网络(~5k参数), 同时成立过曝光和欠曝光问题, 效果不错. 2) 用一个illumination net预测原图和1-原图的illumination, 用来解决retinex理论不能处理过曝的局限. 然后把欠曝光修复结果, 过曝修复结果和原图送到fusion net中预测三个分量的权重, 进行加权融合. 最后用一个restoration net去除噪声和artifacts

  • Integrating Semantic Segmentation and Retinex Model for Low Light Image Enhancement
    Minhao Fan, Wenjing Wang, Wenhan Yang, Jiaying Liu
    [MM 2020] [Project]
    [★] 将分割特征与Retinex网络结合做亮度增强

  • DALE : Dark Region-Aware Low-light Image Enhancement
    Dokyeong Kwon, Guisik Kim, Junseok Kwon
    [BMVC 2020] [Pytorch-Code]
    [★] 通过改变每个超像素的亮度生成了一个数据集, 用来训练一个attention网络. 感觉一般.

  • Zero-Shot Restoration of Underexposed Images via Robust Retinex Decomposition
    Anqi Zhu, Lin Zhang, Ying Shen, Yong Ma, Shengjie Zhao, Yicong Zhou
    [ICME 2020] [Pytorch-Code]
    [RRDNet]

  • Low-Light Image Enhancement via a Deep Hybrid Network
    Wenqi Ren, Sifei Liu, Lin Ma, Qianqian Xu, Xiangyu Xu, Xiaochun Cao, Junping Du, Ming-Hsuan Yang
    [TIP 2019] [Code]
    [☆] 分为全局对比度增强和细节增强两支, 细节部分使用了RNN

  • Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low Light Image Enhancement
    Yang Wang, Yang Cao, Zheng-Jun Zha, Jing Zhang, Zhiwei Xiong, Wei Zhang, Feng Wu
    [MM 2019]

  • Kindling the Darkness: A Practical Low light Image Enhancer
    Yonghua Zhang, Jiawan Zhang, Xiaojie Guo
    [MM 2019] [TF-Code-KinD] [TF-Code-KinD++]
    [KinD] [★★] 1) 采用类似Retinex的结构, 两个分支分别预测亮度分量和反射分量. 网络结构和loss可以参考. 2) 提出了一个小型的亮度adjustment net, 可以输入一个ratio, 控制增强程度, 比较有趣.

  • Underexposed Photo Enhancement Using Deep Illumination Estimation
    Ruixing Wang, Qing Zhang, Chi-Wing Fu, Xiaoyong Shen, Wei-Shi Zheng, Jiaya Jia
    [CVPR 2019] [TF-code]
    [DeepUPE] [★] 同样基于Retinex理论, 但网络只预测illumination map, 使用了reconstruction, color和smooth loss. 整个工程都建立在HDRNet的基础上. 用联合上采样的思路做tone mapping的思路感觉可以挖掘一下.

  • Learning digital camera pipeline for extreme low-light imaging
    Syed Waqas Zamir, Aditya Arora, Salman Khan, Fahad Shahbaz Khan, Ling Shao
    [arXiv 1904]

  • EnlightenGAN: Deep Light Enhancement without Paired Supervision
    Yifan Jiang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, Zhangyang Wang
    [arXiv 1906] [Pytorch-code]
    [★★] 基于GAN的非监督亮度增强方法, 效果不错

  • Low-light Image Enhancement Algorithm Based on Retinex and Generative Adversarial Network
    Yangming Shi, Xiaopo Wu, Ming Zhu
    [arXiv 1906]
    [Retinex-GAN] [☆]

  • Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset
    Feifan Lv, Yu Li, Feng Lu
    [arXiv 1908] [Project]
    [★☆] 1) 同时做tone mapping和去噪, 分为亮度attention map预测, noise map预测, 多尺度增强模块和refine模块四部分, 网络结构和loss可以参考. 2) 提出了一个生成低光照加噪声数据的流程.

  • Color-wise Attention Network for Low-light Image Enhancement
    Yousef Atoum, Mao Ye, Liu Ren, Ying Tai, Xiaoming Liu
    [arXiv 1911]
    [★] 亮度和颜色通道分两只分别增强的方案, 其中color和point的attention部分没看懂

  • Exposure: A White-Box Photo Post-Processing Framework
    Yuanming Hu, Hao He, Chenxi Xu, Baoyuan Wang, Stephen Lin
    [SIGGRAPH 2018] [TF-Code]
    [★] 胡渊明在图像质量增强领域的一篇论文, 用增强学习对图像进行对比度, 曝光度, gamma等方面的校正. 由于实际部署的限制, 目前未对增强学习有所了解.

  • Learning a Deep Single Image Contrast Enhancer from Multi-Exposure Images
    Jianrui Cai, Shuhang Gu, Lei Zhang
    [TIP 2018] [Caffe-Code]
    [SICE] [★★] MEF

  • GLADNet: Low-Light Enhancement Network with Global Awareness
    Wenjing Wang,Chen Wei, Wenhan Yang, Jiaying Liu
    [FG 2018] [Project] [TF-Code]
    [☆] encoder-decoder + refine结构的网络

  • LightenNet: A Convolutional Neural Network For Weakly Illuminated Image Enhancement
    Chongyi Li, Jichang Guo, Fatih Porikli, Yanwei Pang
    [PRL 2018] [Project]

  • Deep Retinex Decomposition for Low-Light Enhancement
    Chen Wei, Wenjing Wang, Wenhan Yang, Jiaying Liu
    [BMVC 2018 Oral] [Project] [TF-Code]
    [RetinexNet] [★] 基于retinex理论设计的网络, 后续一些工作基于这个思路展开, 但本文的效果一般

  • MBLLEN: Low-light Image/Video Enhancement Using CNNs
    Feifan Lv, Feng Lu, Jianhua Wu, Chongsoon Lim
    [BMVC 2018] [Page] [TF-Code]
    [★] 多分支亮度增强网络

  • Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs
    Yu-Sheng Chen, Yu-Ching Wang, Man-Hsin Kao, Yung-Yu Chuang
    [CVPR 2018 Spotlight] [TF-Code] [TF-Code2]
    [★☆] UNet + cycGAN, 无需paired样本的图像增强方法, 可以参考, 只是代码有一点点乱

  • Distort-and-recover: Color Enhancement Using Deep Reinforcement Learning
    Jongchan Park, Joon-Young Lee, Donggeun Yoo, In So Kweon
    [CVPR 2018] [TF-Code]

  • DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning
    Runsheng Yu, Wenyu Liu, Yasen Zhang, Zhi Qu, Deli Zhao, Bo Zhang
    [NIPS 2018]

  • LECARM: Low-Light Image Enhancement Using the Camera Response Model
    Yurui Ren; Zhenqiang Ying; Thomas H. Li; Ge Li
    [TCS 2018]
    [★] (传统方法) 利用CRF和BTF做增强

  • MSR-net:Low-light Image Enhancement Using Deep Convolutional Network
    Liang Shen, Zihan Yue, Fan Feng, Quan Chen, Shihao Liu, Jie Ma
    [arXiv 1711]
    [★☆] 用CNN做亮度增强较早的一篇, 个人觉得该网络结构可能未必效果很好, 但思路值得学习. 本文认为传统的MSR(multi scale Retinex)在实际应用中可以DoG的形式近似, 不同核的高斯函数可用若干个卷积stack代替. 提出的网络首先将低光照输入做不同程度的亮度调整并变换到log域, 之后再仿照MSR的形式用CNN对输入进行亮度增强, 最后是一个1x1的颜色恢复模块.

  • A New Image Contrast Enhancement Algorithm Using Exposure Fusion Framework
    Zhenqiang Ying, Ge Li, Yurui Ren, Ronggang Wang, Wenmin Wang
    [CAIP 2017] [Project] [Matlab-Code] [Python-Code]
    [★★] 大致浏览, 利用原图和曝光增强后的图像融合, 提升亮度和对比度. 融合权值通过求解光照强度得到, 曝光增强图通过作者之前提出的相机响应校正模型得到.