Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-7

Low-Light Image Enhancement

3260 papers • 126 benchmarks • 313 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.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in low-light-image-enhancement-7

Trend

Dataset

Best Model

Actions

LOL

LOL

LOLv2

LOLv2

LOLv2-synthetic

LOLv2-synthetic

Libraries

i

Use these libraries to find low-light-image-enhancement-7 models and implementations

2 papers 166

Datasets

LOL

3DMatch

AFLW

SID

LLVIP

DICM

Subtasks

No subtasks available.

Most implemented papers

SSD: Single Shot MultiBox Detector

Christian Szegedy, D. Erhan, A. Berg, Scott E. Reed, W. Liu, Dragomir Anguelov, Cheng-Yang Fu•Mon Dec 07 2015

The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component.

33666

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

MEF

MEF

VV

VV

NPE

NPE

LIME

LIME

DICM

DICM

LOL-v2

LOL-v2

Sony-Total-Dark

Sony-Total-Dark

SID

SID

LOL-v2-synthetic

LOL-v2-synthetic

AFLW (Zhang CVPR 2018 crops)

AFLW (Zhang CVPR 2018 crops)

3DMatch Benchmark

3DMatch Benchmark

10 Monkey Species

10 Monkey Species

MIT-Adobe FiveK

MIT-Adobe FiveK

Nikon RAW Low Light

Nikon RAW Low Light

Canon RAW Low Light

Canon RAW Low Light

SMID

SMID

SDSD-indoor

SDSD-indoor

SDSD-outdoor

SDSD-outdoor

LSRW

LSRW

cuiziteng/iccv_maet

2 papers 166

ExDark

ExDark

MIT-Adobe FiveK

MIT-Adobe FiveK

LOL-v2

SMID

0

Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement

Chen Change Loy, Runmin Cong, Chongyi Li, S. Kwong, Chunle Guo, Junhui Hou, Jichang Guo•Sat Jan 18 2020

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 and shows that it generalizes well to diverse lighting conditions.

1884 0

Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding

Alex Kendall, Vijay Badrinarayanan, R. Cipolla•Sun Nov 08 2015

A practical system which is able to predict pixel-wise class labels with a measure of model uncertainty, and shows that modelling uncertainty improves segmentation performance by 2-3% across a number of state of the art architectures such as SegNet, FCN and Dilation Network, with no additional parametrisation.

1116 0

EnlightenGAN: Deep Light Enhancement Without Paired Supervision

Zhangyang Wang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou•Sun Jun 16 2019

This paper proposes a highly effective unsupervised generative adversarial network, dubbed EnlightenGAN, that can be trained without low/normal-light image pairs, yet proves to generalize very well on various real-world test images.

2003 0

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

S. Sarkar, Kin Gwn Lore, Adedotun Akintayo•Wed Nov 11 2015

It is shown that a variant of the stacked-sparse denoising autoencoder can learn from synthetically darkened and noise-added training examples to adaptively enhance images taken from natural low-light environment and/or are hardware-degraded.

1687 0

Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement

Radu Timofte, Haoqian Wang, Jing Lin, Yulun Zhang, Hao Bian•Sat Mar 11 2023

A simple yet principled One-stage Retinex-based Framework (ORF), designed an Illumination-Guided Transformer (IGT) that utilizes illumination representations to direct the modeling of non-local interactions of regions with different lighting conditions, and obtains the algorithm, Retinexformer.

493 0

Kindling the Darkness: A Practical Low-light Image Enhancer

Xiaojie Guo, Jiawan Zhang, Yonghua Zhang•Fri May 03 2019

This work builds a simple yet effective network for Kindling the Darkness (denoted as KinD), which, inspired by Retinex theory, decomposes images into two components that are robust against severe visual defects, and user-friendly to arbitrarily adjust light levels.

1518 0

Deep Retinex Decomposition for Low-Light Enhancement

Jiaying Liu, Wenhan Yang, Wenjing Wang, Chen Wei•Mon Aug 13 2018

Extensive experiments demonstrate that the proposed deep Retinex-Net learned on this LOw-Light dataset not only achieves visually pleasing quality for low-light enhancement but also provides a good representation of image decomposition.

2285 0

Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation Dataset

Yu Li, Feng Lu, Feifan Lv•Thu Aug 01 2019

This paper proposes a novel end-to-end attention-guided method based on multi-branch convolutional neural network that can produce high fidelity enhancement results for low-light images and outperforms the current state-of-the-art methods both quantitatively and visually.

308 0

Test-Time Training with Self-Supervision for Generalization under Distribution Shifts

Moritz Hardt, John Miller, Alexei A. Efros, Zhuang Liu, X. Wang, Yu Sun•Sat Sep 28 2019

This work turns a single unlabeled test sample into a self-supervised learning problem, on which the model parameters are updated before making a prediction, which leads to improvements on diverse image classification benchmarks aimed at evaluating robustness to distribution shifts.

1101 0

Adding a benchmark result helps the community track progress.

Low-Light Image Enhancement | State-of-the-Art