Low-Light Image Enhancement
166 papers with code • 22 benchmarks • 23 datasets
Low-Light Image Enhancement is a computer vision task that involves improving the quality of images captured under low-light conditions. The goal of low-light image enhancement is to make images brighter, clearer, and more visually appealing, without introducing too much noise or distortion.
Benchmarks
These leaderboards are used to track progress in Low-Light Image Enhancement
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Low-Light Image Enhancement models and implementations
LOL
3DMatch
AFLW
SID
LLVIP
DICM
ExDark
MIT-Adobe FiveK
LOL-v2
Most implemented papers
SSD: Single Shot MultiBox Detector
Experimental results on the PASCAL VOC, MS COCO, and ILSVRC datasets confirm that SSD has comparable accuracy to methods that utilize an additional object proposal step and is much faster, while providing a unified framework for both training and inference.
Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
Semantic segmentation is an important tool for visual scene understanding and a meaningful measure of uncertainty is essential for decision making.
Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement
Li-Chongyi/Zero-DCE
•
•
CVPR 2020
The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network.
EnlightenGAN: Deep Light Enhancement without Paired Supervision
Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data?
LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement
In surveillance, monitoring and tactical reconnaissance, gathering the right visual information from a dynamic environment and accurately processing such data are essential ingredients to making informed decisions which determines the success of an operation.
Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement
caiyuanhao1998/retinexformer
•
•
ICCV 2023
When enhancing low-light images, many deep learning algorithms are based on the Retinex theory.
Kindling the Darkness: A Practical Low-light Image Enhancer
zhangyhuaee/KinD
•
•
It is worth to note that our network is trained with paired images shot under different exposure conditions, instead of using any ground-truth reflectance and illumination information.
Deep Retinex Decomposition for Low-Light Enhancement
Based on the decomposition, subsequent lightness enhancement is conducted on illumination by an enhancement network called Enhance-Net, and for joint denoising there is a denoising operation on reflectance.
Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset
yu-li/AGLLNet
•
•
Low-light image enhancement is challenging in that it needs to consider not only brightness recovery but also complex issues like color distortion and noise, which usually hide in the dark.
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
yueatsprograms/ttt_cifar_release
•
•
In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions.
