# NightHaze: Nighttime Image Dehazing via Self-Prior Learning

arXiv: https://arxiv.org/abs/2403.07408 · HTML: https://mlsanity.com/paper/2403.07408/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 64 references that are in the map.
- First posted on arXiv 12 Mar 2024.

## Builds on (most cited first, 28 of 28)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016)
- [FFA-Net: Feature Fusion Attention Network for Single Image Dehazing](https://mlsanity.com/paper/1911.07559/) (2019)
- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [Multi-Scale Boosted Dehazing Network with Dense Feature Fusion](https://mlsanity.com/paper/2004.13388/) (2020)
- [GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing](https://mlsanity.com/paper/1908.03245/) (2019)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models](https://mlsanity.com/paper/2207.14626/) (2022)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency](https://mlsanity.com/paper/2108.06858/) (2021)
- [Densely Connected Pyramid Dehazing Network](https://mlsanity.com/paper/1803.08396/) (2018)
- [Gated Fusion Network for Single Image Dehazing](https://mlsanity.com/paper/1804.00213/) (2018)
- [Domain Adaptation for Image Dehazing](https://mlsanity.com/paper/2005.04668/) (2020)
- [Iterative Prompt Learning for Unsupervised Backlit Image Enhancement](https://mlsanity.com/paper/2303.17569/) (2023)
- [Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression](https://mlsanity.com/paper/2207.10564/) (2022)
- [You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network](https://mlsanity.com/paper/2006.16829/) (2020)
- [Nighttime Dehazing with a Synthetic Benchmark](https://mlsanity.com/paper/2008.03864/) (2020)
- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [Unsupervised Single Image Dehazing Using Dark Channel Prior Loss](https://mlsanity.com/paper/1812.07051/) (2018)
- [End-to-End Single Image Fog Removal using Enhanced Cycle Consistent Adversarial Networks](https://mlsanity.com/paper/1902.01374/) (2019)

## Built on by (most cited first, 23 of 23)

- [JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration](https://mlsanity.com/paper/2504.04158/) (2025)
- [Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation](https://mlsanity.com/paper/2504.03193/) (2025)
- [NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results](https://mlsanity.com/paper/2504.12711/) (2025)
- [NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results](https://mlsanity.com/paper/2604.10634/) (2026)
- [RGB-to-Polarization Estimation: A New Task and Benchmark Study](https://mlsanity.com/paper/2505.13050/) (2025)
- [CLIP-Guided Data Augmentation for Night-Time Image Dehazing](https://mlsanity.com/paper/2604.05500/) (2026)
- [Bridging Day and Night: Target-Class Hallucination Suppression in Unpaired Image Translation](https://mlsanity.com/paper/2602.15383/) (2026)
- [GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion](https://mlsanity.com/paper/2510.03110/) (2025)
- [Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal](https://mlsanity.com/paper/2502.10714/) (2025)
- [Seeing Beyond Haze: Generative Nighttime Image Dehazing](https://mlsanity.com/paper/2503.08073/) (2025)
- [OmniRaindrop: A Comprehensive Benchmark for Dual-Focused Raindrop Removal under Day and Night Scenes](https://mlsanity.com/paper/2510.17719/) (2025)
- [UDPNet: Unleashing Depth-based Priors for Robust Image Dehazing](https://mlsanity.com/paper/2601.06909/) (2026)
- [Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restoration](https://mlsanity.com/paper/2505.16479/) (2025)
- [GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes](https://mlsanity.com/paper/2605.23602/) (2026)
- [Sampling Control for Imbalanced Calibration in Semi-Supervised Learning](https://mlsanity.com/paper/2511.18773/) (2025)
- [Enhanced Polarization Locking in VCSELs](https://mlsanity.com/paper/2604.01857/) (2026)
- [The Devil is in the Darkness: Diffusion-Based Nighttime Dehazing Anchored in Brightness Perception](https://mlsanity.com/paper/2506.02395/) (2025)
- [Nighttime Hazy Image Enhancement via Progressively and Mutually Reinforcing Night-Haze Priors](https://mlsanity.com/paper/2601.01998/) (2026)
- [Transmittance-Guided Structure-Texture Decomposition for Nighttime Image Dehazing](https://mlsanity.com/paper/2603.29507/) (2026)
- [HistoFusionNet: Histogram-Guided Fusion and Frequency-Adaptive Refinement for Nighttime Image Dehazing](https://mlsanity.com/paper/2604.03800/) (2026)
- [Deep Light Pollution Removal in Night Cityscape Photographs](https://mlsanity.com/paper/2604.09145/) (2026)
- [Di2CycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schr"odinger Bridge Transformer](https://mlsanity.com/paper/2608.29043/) (2026)
- [SenseWeather: Multimodal Sensing for Robust Robotic Perception under Extreme Conditions](https://mlsanity.com/paper/2610.14082/) (2026)

## Abstract (arXiv)

Masked autoencoder (MAE) shows that severe augmentation during training produces robust representations for high-level tasks. This paper brings the MAE-like framework to nighttime image enhancement, demonstrating that severe augmentation during training produces strong network priors that are resilient to real-world night haze degradations. We propose a novel nighttime image dehazing method with self-prior learning. Our main novelty lies in the design of severe augmentation, which allows our model to learn robust priors. Unlike MAE that uses masking, we leverage two key challenging factors of nighttime images as augmentation: light effects and noise. During training, we intentionally degrade clear images by blending them with light effects as well as by adding noise, and subsequently restore the clear images. This enables our model to learn clear background priors. By increasing the noise values to approach as high as the pixel intensity values of the glow and light effect blended images, our augmentation becomes severe, resulting in stronger priors. While our self-prior learning is considerably effective in suppressing glow and revealing details of background scenes, in some cases, there are still some undesired artifacts that remain, particularly in the forms of over-suppression. To address these artifacts, we propose a self-refinement module based on the semi-supervised teacher-student framework. Our NightHaze, especially our MAE-like self-prior learning, shows that models trained with severe augmentation effectively improve the visibility of input haze images, approaching the clarity of clear nighttime images. Extensive experiments demonstrate that our NightHaze achieves state-of-the-art performance, outperforming existing nighttime image dehazing methods by a substantial margin of 15.5% for MUSIQ and 23.5% for ClipIQA.