# Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement

arXiv: https://arxiv.org/abs/2103.10621 · HTML: https://mlsanity.com/paper/2103.10621/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 64 references that are in the map.
- First posted on arXiv 19 Mar 2021.

## Builds on (most cited first, 27 of 27)

- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (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)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [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)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [CityPersons: A Diverse Dataset for Pedestrian Detection](https://mlsanity.com/paper/1702.05693/) (2017)
- [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018)
- [To learn image super-resolution, use a GAN to learn how to do image degradation first](https://mlsanity.com/paper/1807.11458/) (2018)
- [Lightweight Pyramid Networks for Image Deraining](https://mlsanity.com/paper/1805.06173/) (2018)
- [MSR-net:Low-light Image Enhancement Using Deep Convolutional Network](https://mlsanity.com/paper/1711.02488/) (2017)
- [Is Faster R-CNN Doing Well for Pedestrian Detection?](https://mlsanity.com/paper/1607.07032/) (2016)
- [MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution](https://mlsanity.com/paper/1909.12978/) (2019)
- [Self-supervised Image Enhancement Network: Training with Low Light Images Only](https://mlsanity.com/paper/2002.11300/) (2020)
- [Illuminating Pedestrians via Simultaneous Detection & Segmentation](https://mlsanity.com/paper/1706.08564/) (2017)
- [Exploring Image Enhancement for Salient Object Detection in Low Light Images](https://mlsanity.com/paper/2007.16124/) (2020)
- [Towards Resolving the Challenge of Long-tail Distribution in UAV Images for Object Detection](https://mlsanity.com/paper/2011.03822/) (2020)
- [Texture Synthesis Using Convolutional Neural Networks](https://mlsanity.com/paper/1505.07376/) (2015)
- [Object Detection based on Region Decomposition and Assembly](https://mlsanity.com/paper/1901.08225/) (2019)
- [From Rain Generation to Rain Removal](https://mlsanity.com/paper/2008.03580/) (2020)

## Built on by (most cited first, 13 of 13)

- [Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement](https://mlsanity.com/paper/2304.07039/) (2023)
- [Low-Light Video Enhancement with Synthetic Event Guidance](https://mlsanity.com/paper/2208.11014/) (2022)
- [LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement](https://mlsanity.com/paper/2307.14659/) (2023)
- [Brightness Perceiving for Recursive Low-Light Image Enhancement](https://mlsanity.com/paper/2504.02362/) (2025)
- [Learning a Practical SDR-to-HDRTV Up-conversion using New Dataset and Degradation Models](https://mlsanity.com/paper/2303.13031/) (2023)
- [Real-World Image Super-Resolution by Exclusionary Dual-Learning](https://mlsanity.com/paper/2206.02609/) (2022)
- [Structural Prior Guided Generative Adversarial Transformers for Low-Light Image Enhancement](https://mlsanity.com/paper/2207.07828/) (2022)
- [RCNet: Deep Recurrent Collaborative Network for Multi-View Low-Light Image Enhancement](https://mlsanity.com/paper/2409.04363/) (2024)
- [ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement](https://mlsanity.com/paper/2605.25569/) (2026)
- [Latent Disentanglement for Low Light Image Enhancement](https://mlsanity.com/paper/2408.06245/) (2024)
- [Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework](https://mlsanity.com/paper/2509.05000/) (2025)
- [Fusing Transferred Priors and Physics-based Decomposition for Underwater Image Enhancement](https://mlsanity.com/paper/2606.15648/) (2026)
- [UBLLIE: Unified Backlight and Low-Light Image Enhancement](https://mlsanity.com/paper/2608.04429/) (2026)

## Abstract (arXiv)

Low-light image enhancement aims to improve an image's visibility while keeping its visual naturalness. Different from existing methods tending to accomplish the relighting task directly by ignoring the fidelity and naturalness recovery, we investigate the intrinsic degradation and relight the low-light image while refining the details and color in two steps. Inspired by the color image formulation (diffuse illumination color plus environment illumination color), we first estimate the degradation from low-light inputs to simulate the distortion of environment illumination color, and then refine the content to recover the loss of diffuse illumination color. To this end, we propose a novel Degradation-to-Refinement Generation Network (DRGN). Its distinctive features can be summarized as 1) A novel two-step generation network for degradation learning and content refinement. It is not only superior to one-step methods, but also capable of synthesizing sufficient paired samples to benefit the model training; 2) A multi-resolution fusion network to represent the target information (degradation or contents) in a multi-scale cooperative manner, which is more effective to address the complex unmixing problems. Extensive experiments on both the enhancement task and joint detection task have verified the effectiveness and efficiency of our proposed method, surpassing the SOTA by textit0.70dB on average and 3.18% in mAP, respectively. The code is available at urlhttps://github.com/kuijiang0802/DRGN.