# Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning

arXiv: https://arxiv.org/abs/2203.07677 · HTML: https://mlsanity.com/paper/2203.07677/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 56 references that are in the map.
- First posted on arXiv 15 Mar 2022.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [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)
- [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)
- [Image De-raining Using a Conditional Generative Adversarial Network](https://mlsanity.com/paper/1701.05957/) (2017)
- [Unsupervised Degradation Representation Learning for Blind Super-Resolution](https://mlsanity.com/paper/2104.00416/) (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)
- [Gated Context Aggregation Network for Image Dehazing and Deraining](https://mlsanity.com/paper/1811.08747/) (2018)
- [UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments](https://mlsanity.com/paper/1904.04474/) (2019)
- [Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing](https://mlsanity.com/paper/1805.05308/) (2018)
- [From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data](https://mlsanity.com/paper/2108.02934/) (2021)
- [Dual Contrastive Learning for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2104.07689/) (2021)
- [Unpaired Deep Image Deraining Using Dual Contrastive Learning](https://mlsanity.com/paper/2109.02973/) (2021)
- [You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network](https://mlsanity.com/paper/2006.16829/) (2020)
- [A Disentangling Invertible Interpretation Network for Explaining Latent Representations](https://mlsanity.com/paper/2004.13166/) (2020)
- [Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2108.04547/) (2021)
- [DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network](https://mlsanity.com/paper/2103.07893/) (2021)
- [Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation](https://mlsanity.com/paper/2103.13660/) (2021)

## Built on by (most cited first, 21 of 21)

- [UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning](https://mlsanity.com/paper/2205.01871/) (2022)
- [Towards Unified Deep Image Deraining: A Survey and A New Benchmark](https://mlsanity.com/paper/2310.03535/) (2023)
- [Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network](https://mlsanity.com/paper/2406.07966/) (2024)
- [Mutual Information-driven Triple Interaction Network for Efficient Image Dehazing](https://mlsanity.com/paper/2308.06998/) (2023)
- [ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing](https://mlsanity.com/paper/2404.17825/) (2024)
- [RSDehamba: Lightweight Vision Mamba for Remote Sensing Satellite Image Dehazing](https://mlsanity.com/paper/2405.10030/) (2024)
- [Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing](https://mlsanity.com/paper/2507.01275/) (2025)
- [Non-aligned supervision for Real Image Dehazing](https://mlsanity.com/paper/2303.04940/) (2023)
- [Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance](https://mlsanity.com/paper/2405.09996/) (2024)
- [HazeFlow: Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing](https://mlsanity.com/paper/2509.18190/) (2025)
- [Unsupervised Variational Translator for Bridging Image Restoration and High-Level Vision Tasks](https://mlsanity.com/paper/2408.08149/) (2024)
- [CAS-GAN for Contrast-free Angiography Synthesis](https://mlsanity.com/paper/2410.08490/) (2024)
- [Continual Learning-Based Unified Model for Unpaired Image Restoration Tasks](https://mlsanity.com/paper/2507.19184/) (2025)
- [PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing](https://mlsanity.com/paper/2604.07048/) (2026)
- [Uni-Removal: A Semi-Supervised Framework for Simultaneously Addressing Multiple Degradations in Real-World Images](https://mlsanity.com/paper/2307.05075/) (2023)
- [Learning Image Deraining Transformer Network with Dynamic Dual Self-Attention](https://mlsanity.com/paper/2308.07781/) (2023)
- [Learning Unpaired Image Dehazing with Physics-based Rehazy Generation](https://mlsanity.com/paper/2506.12824/) (2025)
- [Learning Implicit Neural Degradation Representation for Unpaired Image Dehazing](https://mlsanity.com/paper/2511.13110/) (2025)
- [Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusion](https://mlsanity.com/paper/2603.21820/) (2026)
- [Efficient Real-World Dehazing via Physics-Inspired Global-Local Decoupling](https://mlsanity.com/paper/2606.25732/) (2026)
- [Unpaired Joint Distribution Modeling via Multi-Scale Image Representations](https://mlsanity.com/paper/2607.08198/) (2026)

## Abstract (arXiv)

We offer a practical unpaired learning based image dehazing network from an unpaired set of clear and hazy images. This paper provides a new perspective to treat image dehazing as a two-class separated factor disentanglement task, i.e, the task-relevant factor of clear image reconstruction and the task-irrelevant factor of haze-relevant distribution. To achieve the disentanglement of these two-class factors in deep feature space, contrastive learning is introduced into a CycleGAN framework to learn disentangled representations by guiding the generated images to be associated with latent factors. With such formulation, the proposed contrastive disentangled dehazing method (CDD-GAN) employs negative generators to cooperate with the encoder network to update alternately, so as to produce a queue of challenging negative adversaries. Then these negative adversaries are trained end-to-end together with the backbone representation network to enhance the discriminative information and promote factor disentanglement performance by maximizing the adversarial contrastive loss. During the training, we further show that hard negative examples can suppress the task-irrelevant factors and unpaired clear exemples can enhance the task-relevant factors, in order to better facilitate haze removal and help image restoration. Extensive experiments on both synthetic and real-world datasets demonstrate that our method performs favorably against existing unpaired dehazing baselines.