# ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement

arXiv: https://arxiv.org/abs/2107.05830 · HTML: https://mlsanity.com/paper/2107.05830/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 13 Jul 2021.

## Builds on (most cited first, 15 of 15)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (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)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [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)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [Non-Local Recurrent Network for Image Restoration](https://mlsanity.com/paper/1806.02919/) (2018)
- [Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning](https://mlsanity.com/paper/1804.04450/) (2018)
- [Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning](https://mlsanity.com/paper/1804.03312/) (2018)
- [Exposure: A White-Box Photo Post-Processing Framework](https://mlsanity.com/paper/1709.09602/) (2017)
- [Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing](https://mlsanity.com/paper/1811.04323/) (2018)
- [R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery](https://mlsanity.com/paper/2107.05318/) (2021)

## Built on by (most cited first, 26 of 26)

- [Low-Light Image Enhancement with Wavelet-based Diffusion Models](https://mlsanity.com/paper/2306.00306/) (2023)
- [ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal](https://mlsanity.com/paper/2212.04711/) (2022)
- [ShadowFormer: Global Context Helps Image Shadow Removal](https://mlsanity.com/paper/2302.01650/) (2023)
- [ExposureDiffusion: Learning to Expose for Low-light Image Enhancement](https://mlsanity.com/paper/2307.07710/) (2023)
- [Low-light Image Enhancement via CLIP-Fourier Guided Wavelet Diffusion](https://mlsanity.com/paper/2401.03788/) (2024)
- [Aleth-NeRF: Low-light Condition View Synthesis with Concealing Fields](https://mlsanity.com/paper/2303.05807/) (2023)
- [Enhancement by Your Aesthetic: An Intelligible Unsupervised Personalized Enhancer for Low-Light Images](https://mlsanity.com/paper/2207.07317/) (2022)
- [PIE: Physics-inspired Low-light Enhancement](https://mlsanity.com/paper/2404.04586/) (2024)
- [ALL-E: Aesthetics-guided Low-light Image Enhancement](https://mlsanity.com/paper/2304.14610/) (2023)
- [Brighten-and-Colorize: A Decoupled Network for Customized Low-Light Image Enhancement](https://mlsanity.com/paper/2308.03029/) (2023)
- [Self-Reference Deep Adaptive Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2308.08197/) (2023)
- [Equipping Diffusion Models with Differentiable Spatial Entropy for Low-Light Image Enhancement](https://mlsanity.com/paper/2404.09735/) (2024)
- [ReviveDiff: A Universal Diffusion Model for Restoring Images in Adverse Weather Conditions](https://mlsanity.com/paper/2409.18932/) (2024)
- [REPNP: Plug-and-Play with Deep Reinforcement Learning Prior for Robust Image Restoration](https://mlsanity.com/paper/2207.12056/) (2022)
- [Crowd-Powered Photo Enhancement Featuring an Active Learning Based Local Filter](https://mlsanity.com/paper/2306.09321/) (2023)
- [ECAFormer: Low-light Image Enhancement using Cross Attention](https://mlsanity.com/paper/2406.13281/) (2024)
- [ReF-LLE: Personalized Low-Light Enhancement via Reference-Guided Deep Reinforcement Learning](https://mlsanity.com/paper/2506.22216/) (2025)
- [CURVE: CLIP-Utilized Reinforcement Learning for Visual Image Enhancement via Simple Image Processing](https://mlsanity.com/paper/2505.23102/) (2025)
- [KinD-LCE Curve Estimation And Retinex Fusion On Low-Light Image](https://mlsanity.com/paper/2207.09210/) (2022)
- [Bio-Inspired Simple Neural Network for Low-Light Image Restoration: A Minimalist Approach](https://mlsanity.com/paper/2305.01844/) (2023)
- [Diffusion Models for Low-Light Image Enhancement: A Multi-Perspective Taxonomy and Performance Analysis](https://mlsanity.com/paper/2510.05976/) (2025)
- [Diffusion-Based Low-Light Image Enhancement with Color and Luminance Priors](https://mlsanity.com/paper/2603.00337/) (2026)
- [Whispering to a Blackbox: Bootstrapping Frozen OCR with Visual Prompts](https://mlsanity.com/paper/2603.05276/) (2026)
- [Self-DACE++: Robust Low-Light Enhancement via Efficient Adaptive Curve Estimation](https://mlsanity.com/paper/2604.25367/) (2026)
- [SPARK: Spatial Policy-driven Adaptive Reinforcement learning for Knowledge distillation](https://mlsanity.com/paper/2606.15243/) (2026)
- [Low-light Image Enhancement via Multi-scale Attention combined with Fourier Transform](https://mlsanity.com/paper/2607.24002/) (2026)

## Abstract (arXiv)

Low-light image enhancement (LLIE) is a pervasive yet challenging problem, since: 1) low-light measurements may vary due to different imaging conditions in practice; 2) images can be enlightened subjectively according to diverse preferences by each individual. To tackle these two challenges, this paper presents a novel deep reinforcement learning based method, dubbed ReLLIE, for customized low-light enhancement. ReLLIE models LLIE as a markov decision process, i.e., estimating the pixel-wise image-specific curves sequentially and recurrently. Given the reward computed from a set of carefully crafted non-reference loss functions, a lightweight network is proposed to estimate the curves for enlightening of a low-light image input. As ReLLIE learns a policy instead of one-one image translation, it can handle various low-light measurements and provide customized enhanced outputs by flexibly applying the policy different times. Furthermore, ReLLIE can enhance real-world images with hybrid corruptions, e.g., noise, by using a plug-and-play denoiser easily. Extensive experiments on various benchmarks demonstrate the advantages of ReLLIE, comparing to the state-of-the-art methods.