# Unsupervised Single Image Dehazing Using Dark Channel Prior Loss

arXiv: https://arxiv.org/abs/1812.07051 · HTML: https://mlsanity.com/paper/1812.07051/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2018.

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

- [TAPE: Task-Agnostic Prior Embedding for Image Restoration](https://mlsanity.com/paper/2203.06074/) (2022)
- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning](https://mlsanity.com/paper/2205.01871/) (2022)
- [Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal](https://mlsanity.com/paper/2210.03061/) (2022)
- [NightHaze: Nighttime Image Dehazing via Self-Prior Learning](https://mlsanity.com/paper/2403.07408/) (2024)
- [A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning](https://mlsanity.com/paper/2106.03323/) (2021)
- [Iterative Predictor-Critic Code Decoding for Real-World Image Dehazing](https://mlsanity.com/paper/2503.13147/) (2025)
- [Multi-Scale Single Image Dehazing Using Laplacian and Gaussian Pyramids](https://mlsanity.com/paper/2111.05700/) (2021)
- [Prompt-based test-time real image dehazing: a novel pipeline](https://mlsanity.com/paper/2309.17389/) (2023)
- [Dual-Scale Single Image Dehazing Via Neural Augmentation](https://mlsanity.com/paper/2209.05913/) (2022)
- [Dual Degradation Representation for Joint Deraining and Low-Light Enhancement in the Dark](https://mlsanity.com/paper/2305.03997/) (2023)
- [T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing](https://mlsanity.com/paper/2106.02809/) (2021)
- [Rank-One Prior: Toward Real-Time Scene Recovery](https://mlsanity.com/paper/2103.17126/) (2021)
- [FogAdapt: Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Images](https://mlsanity.com/paper/2201.02588/) (2022)
- [Illumination Controllable Dehazing Network based on Unsupervised Retinex Embedding](https://mlsanity.com/paper/2306.05675/) (2023)
- [CoA: Towards Real Image Dehazing via Compression-and-Adaptation](https://mlsanity.com/paper/2504.05590/) (2025)
- [Dehazing-NeRF: Neural Radiance Fields from Hazy Images](https://mlsanity.com/paper/2304.11448/) (2023)
- [DehazeGS: Seeing Through Fog with 3D Gaussian Splatting](https://mlsanity.com/paper/2501.03659/) (2025)
- [Seeing Beyond Haze: Generative Nighttime Image Dehazing](https://mlsanity.com/paper/2503.08073/) (2025)
- [Priors in Deep Image Restoration and Enhancement: A Survey](https://mlsanity.com/paper/2206.02070/) (2022)
- [Harmonizing Light and Darkness: A Symphony of Prior-guided Data Synthesis and Adaptive Focus for Nighttime Flare Removal](https://mlsanity.com/paper/2404.00313/) (2024)
- [Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN](https://mlsanity.com/paper/2204.10970/) (2022)
- [A Practical Framework for Unsupervised Structure Preservation Medical Image Enhancement](https://mlsanity.com/paper/2304.01864/) (2023)
- [Advanced Multiple Linear Regression Based Dark Channel Prior Applied on Dehazing Image and Generating Synthetic Haze](https://mlsanity.com/paper/2103.07065/) (2021)
- [Rich Feature Distillation with Feature Affinity Module for Efficient Image Dehazing](https://mlsanity.com/paper/2207.11250/) (2022)
- [Unpaired Overwater Image Defogging Using Prior Map Guided CycleGAN](https://mlsanity.com/paper/2212.12116/) (2022)
- [Single Image Dehazing Using Scene Depth Ordering](https://mlsanity.com/paper/2408.05683/) (2024)
- [Zero-Reference Image Restoration for Under-Display Camera of UAV](https://mlsanity.com/paper/2202.06283/) (2022)
- [RTE-FM-Dehazer: Radiative Transfer Equation Inspired Flow Matching for Real-World Image Dehazing](https://mlsanity.com/paper/2607.01748/) (2026)
- [HazeSpikeMamba: Coupling Spiking-Inspired and State-Space Features for Self-Supervised Real-World Dehazing](https://mlsanity.com/paper/2608.06886/) (2026)

## Abstract (arXiv)

Single image dehazing is a critical stage in many modern-day autonomous vision applications. Early prior-based methods often involved a time-consuming minimization of a hand-crafted energy function. Recent learning-based approaches utilize the representational power of deep neural networks (DNNs) to learn the underlying transformation between hazy and clear images. Due to inherent limitations in collecting matching clear and hazy images, these methods resort to training on synthetic data; constructed from indoor images and corresponding depth information. This may result in a possible domain shift when treating outdoor scenes. We propose a completely unsupervised method of training via minimization of the well-known, Dark Channel Prior (DCP) energy function. Instead of feeding the network with synthetic data, we solely use real-world outdoor images and tune the network's parameters by directly minimizing the DCP. Although our "Deep DCP" technique can be regarded as a fast approximator of DCP, it actually improves its results significantly. This suggests an additional regularization obtained via the network and learning process. Experiments show that our method performs on par with large-scale supervised methods.