# A Two-stage Unsupervised Approach for Low light Image Enhancement

arXiv: https://arxiv.org/abs/2010.09316 · HTML: https://mlsanity.com/paper/2010.09316/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks](https://mlsanity.com/paper/2303.15710/) (2023)
- [Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving](https://mlsanity.com/paper/2404.04804/) (2024)
- [Boosting Light-Weight Depth Estimation Via Knowledge Distillation](https://mlsanity.com/paper/2105.06143/) (2021)
- [A Lightweight Low-Light Image Enhancement Network via Channel Prior and Gamma Correction](https://mlsanity.com/paper/2402.18147/) (2024)
- [CDAN: Convolutional dense attention-guided network for low-light image enhancement](https://mlsanity.com/paper/2308.12902/) (2023)
- [Data relativistic uncertainty framework for low-illumination anime scenery image enhancement](https://mlsanity.com/paper/2512.21944/) (2025)
- [Towards Predicting Fine Finger Motions from Ultrasound Images via Kinematic Representation](https://mlsanity.com/paper/2202.05204/) (2022)
- [RTFDNet: Fusion-Decoupling for Robust RGB-T Segmentation](https://mlsanity.com/paper/2603.09149/) (2026)

## Abstract (arXiv)

As vision based perception methods are usually built on the normal light assumption, there will be a serious safety issue when deploying them into low light environments. Recently, deep learning based methods have been proposed to enhance low light images by penalizing the pixel-wise loss of low light and normal light images. However, most of them suffer from the following problems: 1) the need of pairs of low light and normal light images for training, 2) the poor performance for dark images, 3) the amplification of noise. To alleviate these problems, in this paper, we propose a two-stage unsupervised method that decomposes the low light image enhancement into a pre-enhancement and a post-refinement problem. In the first stage, we pre-enhance a low light image with a conventional Retinex based method. In the second stage, we use a refinement network learned with adversarial training for further improvement of the image quality. The experimental results show that our method outperforms previous methods on four benchmark datasets. In addition, we show that our method can significantly improve feature points matching and simultaneous localization and mapping in low light conditions.