# ExposureDiffusion: Learning to Expose for Low-light Image Enhancement

arXiv: https://arxiv.org/abs/2307.07710 · HTML: https://mlsanity.com/paper/2307.07710/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 39 of its 53 references that are in the map.
- First posted on arXiv 15 Jul 2023.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 30 of 39)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Improving Diffusion Models for Inverse Problems using Manifold Constraints](https://mlsanity.com/paper/2206.00941/) (2022)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [Deblurring via Stochastic Refinement](https://mlsanity.com/paper/2112.02475/) (2021)
- [Diffusion models as plug-and-play priors](https://mlsanity.com/paper/2206.09012/) (2022)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [SRFlow: Learning the Super-Resolution Space with Normalizing Flow](https://mlsanity.com/paper/2006.14200/) (2020)
- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method](https://mlsanity.com/paper/2212.11548/) (2022)
- [Low-Light Image and Video Enhancement Using Deep Learning: A Survey](https://mlsanity.com/paper/2104.10729/) (2021)
- [A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising](https://mlsanity.com/paper/2003.12751/) (2020)
- [gDDIM: Generalized denoising diffusion implicit models](https://mlsanity.com/paper/2206.05564/) (2022)
- [ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal](https://mlsanity.com/paper/2212.04711/) (2022)
- [Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression](https://mlsanity.com/paper/2207.10564/) (2022)
- [Low-light Image Enhancement via Breaking Down the Darkness](https://mlsanity.com/paper/2111.15557/) (2021)
- [Rethinking Noise Synthesis and Modeling in Raw Denoising](https://mlsanity.com/paper/2110.04756/) (2021)
- [Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2110.00984/) (2021)
- [MSR-net:Low-light Image Enhancement Using Deep Convolutional Network](https://mlsanity.com/paper/1711.02488/) (2017)
- [Deep Equilibrium Approaches to Diffusion Models](https://mlsanity.com/paper/2210.12867/) (2022)
- [Abandoning the Bayer-Filter to See in the Dark](https://mlsanity.com/paper/2203.04042/) (2022)
- [Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low Light Image Enhancement](https://mlsanity.com/paper/1911.11323/) (2019)

## Built on by (most cited first, 29 of 29)

- [SinSR: Diffusion-Based Image Super-Resolution in a Single Step](https://mlsanity.com/paper/2311.14760/) (2023)
- [DarkIR: Robust Low-Light Image Restoration](https://mlsanity.com/paper/2412.13443/) (2024)
- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving](https://mlsanity.com/paper/2404.04804/) (2024)
- [Towards Real-World Blind Face Restoration with Generative Diffusion Prior](https://mlsanity.com/paper/2312.15736/) (2023)
- [Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising](https://mlsanity.com/paper/2405.14304/) (2024)
- [DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts](https://mlsanity.com/paper/2407.03757/) (2024)
- [Learning to See in the Extremely Dark](https://mlsanity.com/paper/2506.21132/) (2025)
- [DiffLLE: Diffusion-guided Domain Calibration for Unsupervised Low-light Image Enhancement](https://mlsanity.com/paper/2308.09279/) (2023)
- [Geometric-Aware Low-Light Image and Video Enhancement via Depth Guidance](https://mlsanity.com/paper/2312.15855/) (2023)
- [Single-Image Shadow Removal Using Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2407.08865/) (2024)
- [DI-Retinex: Digital-Imaging Retinex Theory for Low-Light Image Enhancement](https://mlsanity.com/paper/2404.03327/) (2024)
- [Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection](https://mlsanity.com/paper/2509.09183/) (2025)
- [Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising](https://mlsanity.com/paper/2503.11262/) (2025)
- [LDM-ISP: Enhancing Neural ISP for Low Light with Latent Diffusion Models](https://mlsanity.com/paper/2312.01027/) (2023)
- [Unified-EGformer: Exposure Guided Lightweight Transformer for Mixed-Exposure Image Enhancement](https://mlsanity.com/paper/2407.13170/) (2024)
- [Zero-Shot Low Light Image Enhancement with Diffusion Prior](https://mlsanity.com/paper/2412.13401/) (2024)
- [ClassLIE: Structure- and Illumination-Adaptive Classification for Low-Light Image Enhancement](https://mlsanity.com/paper/2312.13265/) (2023)
- [From Darkness to Detail: Frequency-Aware SSMs for Low-Light Vision](https://mlsanity.com/paper/2408.09650/) (2024)
- [Reversing the Damage: A QP-Aware Transformer-Diffusion Approach for 8K Video Restoration under Codec Compression](https://mlsanity.com/paper/2412.08912/) (2024)
- [TS-Diff: Two-Stage Diffusion Model for Low-Light RAW Image Enhancement](https://mlsanity.com/paper/2505.04281/) (2025)
- [Personalized Generative Low-light Image Denoising and Enhancement](https://mlsanity.com/paper/2412.14327/) (2024)
- [Towards Perfection: Building Inter-component Mutual Correction for Retinex-based Low-light Image Enhancement](https://mlsanity.com/paper/2508.09009/) (2025)
- [UNICE: Training A Universal Image Contrast Enhancer](https://mlsanity.com/paper/2507.17157/) (2025)
- [InfraDiffusion: zero-shot depth map restoration with diffusion models and prompted segmentation from sparse infrastructure point clouds](https://mlsanity.com/paper/2509.03324/) (2025)
- [Boosting Fidelity for Pre-Trained-Diffusion-Based Low-Light Image Enhancement via Condition Refinement](https://mlsanity.com/paper/2510.17105/) (2025)
- [Towards Any-Quality Image Segmentation via Generative and Adaptive Latent Space Enhancement](https://mlsanity.com/paper/2601.02018/) (2026)
- [SIMI: Self-information Mining Network for Low-light Image Enhancement](https://mlsanity.com/paper/2605.07767/) (2026)
- [High-Quality Exposure Correction with Diffusion-Based Image Generation Priors](https://mlsanity.com/paper/2608.08720/) (2026)

## Abstract (arXiv)

Previous raw image-based low-light image enhancement methods predominantly relied on feed-forward neural networks to learn deterministic mappings from low-light to normally-exposed images. However, they failed to capture critical distribution information, leading to visually undesirable results. This work addresses the issue by seamlessly integrating a diffusion model with a physics-based exposure model. Different from a vanilla diffusion model that has to perform Gaussian denoising, with the injected physics-based exposure model, our restoration process can directly start from a noisy image instead of pure noise. As such, our method obtains significantly improved performance and reduced inference time compared with vanilla diffusion models. To make full use of the advantages of different intermediate steps, we further propose an adaptive residual layer that effectively screens out the side-effect in the iterative refinement when the intermediate results have been already well-exposed. The proposed framework can work with both real-paired datasets, SOTA noise models, and different backbone networks. Note that, the proposed framework is compatible with real-paired datasets, real/synthetic noise models, and different backbone networks. We evaluate the proposed method on various public benchmarks, achieving promising results with consistent improvements using different exposure models and backbones. Besides, the proposed method achieves better generalization capacity for unseen amplifying ratios and better performance than a larger feedforward neural model when few parameters are adopted.