# Low-Light Image Enhancement with Normalizing Flow

arXiv: https://arxiv.org/abs/2109.05923 · HTML: https://mlsanity.com/paper/2109.05923/

## Key facts

- Cited by 185 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 13 Sep 2021.

## Builds on (most cited first, 30 of 30)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [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)
- [PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows](https://mlsanity.com/paper/1906.12320/) (2019)
- [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)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Why Normalizing Flows Fail to Detect Out-of-Distribution Data](https://mlsanity.com/paper/2006.08545/) (2020)
- [SRFlow: Learning the Super-Resolution Space with Normalizing Flow](https://mlsanity.com/paper/2006.14200/) (2020)
- [Learning Likelihoods with Conditional Normalizing Flows](https://mlsanity.com/paper/1912.00042/) (2019)
- [Guided Image Generation with Conditional Invertible Neural Networks](https://mlsanity.com/paper/1907.02392/) (2019)
- [Noise Flow: Noise Modeling with Conditional Normalizing Flows](https://mlsanity.com/paper/1908.08453/) (2019)
- [Invertible Image Rescaling](https://mlsanity.com/paper/2005.05650/) (2020)
- [Invertible Denoising Network: A Light Solution for Real Noise Removal](https://mlsanity.com/paper/2104.10546/) (2021)
- [Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset](https://mlsanity.com/paper/1908.00682/) (2019)
- [Conditional Density Estimation with Bayesian Normalising Flows](https://mlsanity.com/paper/1802.04908/) (2018)
- [C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds](https://mlsanity.com/paper/1912.07009/) (2019)
- [MSR-net:Low-light Image Enhancement Using Deep Convolutional Network](https://mlsanity.com/paper/1711.02488/) (2017)
- [A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement](https://mlsanity.com/paper/1711.00591/) (2017)
- [Joint Enhancement and Denoising Method via Sequential Decomposition](https://mlsanity.com/paper/1804.08468/) (2018)
- [DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows](https://mlsanity.com/paper/2101.05796/) (2021)
- [Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low Light Image Enhancement](https://mlsanity.com/paper/1911.11323/) (2019)
- [Conditional Adversarial Generative Flow for Controllable Image Synthesis](https://mlsanity.com/paper/1904.01782/) (2019)

## Built on by (most cited first, 30 of 185)

- [SinSR: Diffusion-Based Image Super-Resolution in a Single Step](https://mlsanity.com/paper/2311.14760/) (2023)
- [Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method](https://mlsanity.com/paper/2212.11548/) (2022)
- [ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal](https://mlsanity.com/paper/2212.04711/) (2022)
- [Global Structure-Aware Diffusion Process for Low-Light Image Enhancement](https://mlsanity.com/paper/2310.17577/) (2023)
- [OneRestore: A Universal Restoration Framework for Composite Degradation](https://mlsanity.com/paper/2407.04621/) (2024)
- [Low-Light Image Enhancement via Structure Modeling and Guidance](https://mlsanity.com/paper/2305.05839/) (2023)
- [Diffusion Models in Low-Level Vision: A Survey](https://mlsanity.com/paper/2406.11138/) (2024)
- [Residual Denoising Diffusion Models](https://mlsanity.com/paper/2308.13712/) (2023)
- [Pyramid Diffusion Models For Low-light Image Enhancement](https://mlsanity.com/paper/2305.10028/) (2023)
- [HVI: A New Color Space for Low-light Image Enhancement](https://mlsanity.com/paper/2502.20272/) (2025)
- [A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends](https://mlsanity.com/paper/2410.15067/) (2024)
- [Zero-Reference Low-Light Enhancement via Physical Quadruple Priors](https://mlsanity.com/paper/2403.12933/) (2024)
- [Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement](https://mlsanity.com/paper/2304.07039/) (2023)
- [Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger](https://mlsanity.com/paper/2302.14677/) (2023)
- [Lighting up NeRF via Unsupervised Decomposition and Enhancement](https://mlsanity.com/paper/2307.10664/) (2023)
- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [ShadowFormer: Global Context Helps Image Shadow Removal](https://mlsanity.com/paper/2302.01650/) (2023)
- [Low-Light Video Enhancement with Synthetic Event Guidance](https://mlsanity.com/paper/2208.11014/) (2022)
- [GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval](https://mlsanity.com/paper/2407.12431/) (2024)
- [CLE Diffusion: Controllable Light Enhancement Diffusion Model](https://mlsanity.com/paper/2308.06725/) (2023)
- [ExposureDiffusion: Learning to Expose for Low-light Image Enhancement](https://mlsanity.com/paper/2307.07710/) (2023)
- [Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restoration](https://mlsanity.com/paper/2501.16583/) (2025)
- [Human Pose Estimation in Extremely Low-Light Conditions](https://mlsanity.com/paper/2303.15410/) (2023)
- [You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement](https://mlsanity.com/paper/2402.05809/) (2024)
- [Perception-Oriented Video Frame Interpolation via Asymmetric Blending](https://mlsanity.com/paper/2404.06692/) (2024)
- [Memories are One-to-Many Mapping Alleviators in Talking Face Generation](https://mlsanity.com/paper/2212.05005/) (2022)
- [Reversible Decoupling Network for Single Image Reflection Removal](https://mlsanity.com/paper/2410.08063/) (2024)
- [Half Wavelet Attention on M-Net+ for Low-Light Image Enhancement](https://mlsanity.com/paper/2203.01296/) (2022)
- [Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognition](https://mlsanity.com/paper/2303.04291/) (2023)
- [Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise](https://mlsanity.com/paper/2311.14900/) (2023)

## Abstract (arXiv)

To enhance low-light images to normally-exposed ones is highly ill-posed, namely that the mapping relationship between them is one-to-many. Previous works based on the pixel-wise reconstruction losses and deterministic processes fail to capture the complex conditional distribution of normally exposed images, which results in improper brightness, residual noise, and artifacts. In this paper, we investigate to model this one-to-many relationship via a proposed normalizing flow model. An invertible network that takes the low-light images/features as the condition and learns to map the distribution of normally exposed images into a Gaussian distribution. In this way, the conditional distribution of the normally exposed images can be well modeled, and the enhancement process, i.e., the other inference direction of the invertible network, is equivalent to being constrained by a loss function that better describes the manifold structure of natural images during the training. The experimental results on the existing benchmark datasets show our method achieves better quantitative and qualitative results, obtaining better-exposed illumination, less noise and artifact, and richer colors.