Awesome-Low-Light-Image-Enhancement

Papers and Codes

HE-Based Algorithm

Todo

Retinex-Based Algorithm

[2016 CVPR] MF: A weighted variational model for simultaneous reflectance and illumination estimation paper code

[2017 TIP] LIME: Low-Light Image Enhancement via Illumination Map Estimation paper code

Denoise-Based Algorithm

Todo

Supervised-Deep-Learning Algorithm

[2020 CVPR] Learning to Restore Low-Light Images via Decomposition-and-Enhancement paper

[2018 BMVC] Retinex-Net: Deep Retinex Decomposition for Low-Light Enhancement paper code

[2018 FG] GLADNet: Low-Light Enhancement Network with Global Awareness paper code

[2018 CVPR] Learning to See in the Dark paper code

Semi-Supervised-Deep-Learning Algorithm

[2020 CVPR] DRBN: From Fidelity to Visual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement paper

Unsupervised-Deep-Learning Algorithm

[2020 CVPR] Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement paer

[2020.2 SPL] Unsupervised Low-Light Image Enhancement Using Bright Channel Prior paper

[2019.6 Preprint] EnlightenGAN: Deep Light Enhancement without Paired Supervision paper codes

Datasets

LOL(LOw-Light): 500 pairs images. Download

GladNet-Dataset: Download

Synthetic Dataset

SID(See In the Dark) Download

MIT-Adobe FiveK Dataset Download

Mertrics

Full Reference Quality Metrics

MSE

PSNR

SSIM

UQI

TQMI

No-Reference Quality Metrics

NIQE

LOE

Related Work

Bak of codes and datasets Baidu Drive Google Drive

Referennce

Citing

@Misc{2020shiALLIE,
	howpublished = {\url{https://github.com/ymmshi/Awesome-Low-Light-Enhancement}},
	title = {Awesome-Low-Light-Image-Enhancement},
	author = {ymshi},
}

If your research interests is related to low-light image enhancement, we can communicate together, my email address: [email protected]

Welcome to pull requests or create issues!