# Self-supervised Low Light Image Enhancement and Denoising

arXiv: https://arxiv.org/abs/2103.00832 · HTML: https://mlsanity.com/paper/2103.00832/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 1 Mar 2021.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Non-Local Recurrent Network for Image Restoration](https://mlsanity.com/paper/1806.02919/) (2018)
- [MSR-net:Low-light Image Enhancement Using Deep Convolutional Network](https://mlsanity.com/paper/1711.02488/) (2017)
- [Joint Enhancement and Denoising Method via Sequential Decomposition](https://mlsanity.com/paper/1804.08468/) (2018)
- [Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement Networks](https://mlsanity.com/paper/2008.11434/) (2020)
- [Learning an Adaptive Model for Extreme Low-light Raw Image Processing](https://mlsanity.com/paper/2004.10447/) (2020)

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

- [Progressive Joint Low-light Enhancement and Noise Removal for Raw Images](https://mlsanity.com/paper/2106.14844/) (2021)
- [No-Reference Image Quality Assessment by Hallucinating Pristine Features](https://mlsanity.com/paper/2108.04165/) (2021)
- [Learnable Differencing Center for Nighttime Depth Perception](https://mlsanity.com/paper/2306.14538/) (2023)
- [Simplifying Low-Light Image Enhancement Networks with Relative Loss Functions](https://mlsanity.com/paper/2304.02978/) (2023)
- [Attention based Broadly Self-guided Network for Low light Image Enhancement](https://mlsanity.com/paper/2112.06226/) (2021)
- [Unsupervised Low Light Image Enhancement Using SNR-Aware Swin Transformer](https://mlsanity.com/paper/2306.02082/) (2023)
- [Generating Animatable 3D Cartoon Faces from Single Portraits](https://mlsanity.com/paper/2307.01468/) (2023)
- [A Multi-Scale Spatial Attention-Based Zero-Shot Learning Framework for Low-Light Image Enhancement](https://mlsanity.com/paper/2506.18323/) (2025)

## Abstract (arXiv)

This paper proposes a self-supervised low light image enhancement method based on deep learning, which can improve the image contrast and reduce noise at the same time to avoid the blur caused by pre-/post-denoising. The method contains two deep sub-networks, an Image Contrast Enhancement Network (ICE-Net) and a Re-Enhancement and Denoising Network (RED-Net). The ICE-Net takes the low light image as input and produces a contrast enhanced image. The RED-Net takes the result of ICE-Net and the low light image as input, and can re-enhance the low light image and denoise at the same time. Both of the networks can be trained with low light images only, which is achieved by a Maximum Entropy based Retinex (ME-Retinex) model and an assumption that noises are independently distributed. In the ME-Retinex model, a new constraint on the reflectance image is introduced that the maximum channel of the reflectance image conforms to the maximum channel of the low light image and its entropy should be the largest, which converts the decomposition of reflectance and illumination in Retinex model to a non-ill-conditioned problem and allows the ICE-Net to be trained with a self-supervised way. The loss functions of RED-Net are carefully formulated to separate the noises and details during training, and they are based on the idea that, if noises are independently distributed, after the processing of smoothing filters (eg mean filter), the gradient of the noise part should be smaller than the gradient of the detail part. It can be proved qualitatively and quantitatively through experiments that the proposed method is efficient.