# Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network

arXiv: https://arxiv.org/abs/2406.07966 · HTML: https://mlsanity.com/paper/2406.07966/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 94 references that are in the map.
- First posted on arXiv 12 Jun 2024.

## Builds on (most cited first, 30 of 58)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos](https://mlsanity.com/paper/2304.01186/) (2023)
- [FFA-Net: Feature Fusion Attention Network for Single Image Dehazing](https://mlsanity.com/paper/1911.07559/) (2019)
- [Deep Unfolding Network for Image Super-Resolution](https://mlsanity.com/paper/2003.10428/) (2020)
- [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)
- [Resolution Adaptive Networks for Efficient Inference](https://mlsanity.com/paper/2003.07326/) (2020)
- [Deep Generalized Unfolding Networks for Image Restoration](https://mlsanity.com/paper/2204.13348/) (2022)
- [Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model](https://mlsanity.com/paper/2308.13164/) (2023)
- [Domain Adaptation for Image Dehazing](https://mlsanity.com/paper/2005.04668/) (2020)
- [Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding](https://mlsanity.com/paper/1808.01265/) (2018)
- [Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping](https://mlsanity.com/paper/2305.11003/) (2023)
- [Agent Attention: On the Integration of Softmax and Linear Attention](https://mlsanity.com/paper/2312.08874/) (2023)
- [UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments](https://mlsanity.com/paper/1904.04474/) (2019)
- [Curricular Contrastive Regularization for Physics-aware Single Image Dehazing](https://mlsanity.com/paper/2303.14218/) (2023)
- [MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing](https://mlsanity.com/paper/2308.14036/) (2023)
- [Regularizing Deep Networks with Semantic Data Augmentation](https://mlsanity.com/paper/2007.10538/) (2020)
- [RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors](https://mlsanity.com/paper/2304.03994/) (2023)
- [Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model](https://mlsanity.com/paper/2311.11638/) (2023)
- [Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation](https://mlsanity.com/paper/2307.11545/) (2023)
- [Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects](https://mlsanity.com/paper/2308.03166/) (2023)

## Built on by (most cited first, 26 of 26)

- [Taming Rectified Flow for Inversion and Editing](https://mlsanity.com/paper/2411.04746/) (2024)
- [Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models](https://mlsanity.com/paper/2508.12880/) (2025)
- [InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences](https://mlsanity.com/paper/2412.01197/) (2024)
- [FastVMT: Eliminating Redundancy in Video Motion Transfer](https://mlsanity.com/paper/2602.05551/) (2026)
- [Integrating Extra Modality Helps Segmentor Find Camouflaged Objects Well](https://mlsanity.com/paper/2502.14471/) (2025)
- [Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing](https://mlsanity.com/paper/2507.01275/) (2025)
- [Reversible Unfolding Network for Concealed Visual Perception with Generative Refinement](https://mlsanity.com/paper/2508.15027/) (2025)
- [PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation](https://mlsanity.com/paper/2603.00976/) (2026)
- [Nested Unfolding Network for Real-World Concealed Object Segmentation](https://mlsanity.com/paper/2511.18164/) (2025)
- [Bilevel Layer-Positioning LoRA for Real Image Dehazing](https://mlsanity.com/paper/2603.10872/) (2026)
- [Photon: Speedup Volume Understanding with Efficient Multimodal Large Language Models](https://mlsanity.com/paper/2603.25155/) (2026)
- [FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration](https://mlsanity.com/paper/2511.14099/) (2025)
- [Exploring Fourier Prior and Event Collaboration for Low-Light Image Enhancement](https://mlsanity.com/paper/2508.00308/) (2025)
- [Exploiting Discriminative Codebook Prior for Autoregressive Image Generation](https://mlsanity.com/paper/2508.10719/) (2025)
- [Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset](https://mlsanity.com/paper/2603.04745/) (2026)
- [Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy](https://mlsanity.com/paper/2605.00719/) (2026)
- [Unrolled Graph Neural Networks for Constrained Optimization](https://mlsanity.com/paper/2509.17156/) (2025)
- [MoKus: Leveraging Cross-Modal Knowledge Transfer for Knowledge-Aware Concept Customization](https://mlsanity.com/paper/2603.12743/) (2026)
- [PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing](https://mlsanity.com/paper/2604.07048/) (2026)
- [HNDiff: Haze-Noise Diffusion for Image Dehazing](https://mlsanity.com/paper/2608.10995/) (2026)
- [Benchmarking Endoscopic Surgical Image Restoration and Beyond](https://mlsanity.com/paper/2505.19161/) (2025)
- [A PDE-Based Image Dehazing Method via Atmospheric Scattering Theory](https://mlsanity.com/paper/2506.08793/) (2025)
- [Learning Unpaired Image Dehazing with Physics-based Rehazy Generation](https://mlsanity.com/paper/2506.12824/) (2025)
- [API: Empowering Generalizable Real-World Image Dehazing via Adaptive Patch Importance Learning](https://mlsanity.com/paper/2601.01992/) (2026)
- [Nighttime Hazy Image Enhancement via Progressively and Mutually Reinforcing Night-Haze Priors](https://mlsanity.com/paper/2601.01998/) (2026)
- [Weather-Conditioned Depth Anything](https://mlsanity.com/paper/2609.04827/) (2026)

## Abstract (arXiv)

Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real haze distributions and the scarcity of paired real-world data. To address these challenges, we first introduce a cooperative unfolding network that jointly models atmospheric scattering and image scenes, effectively integrating physical knowledge into deep networks to restore haze-contaminated details. Additionally, we propose the first RID-oriented iterative mean-teacher framework, termed the Coherence-based Label Generator, to generate high-quality pseudo labels for network training. Specifically, we provide an optimal label pool to store the best pseudo-labels during network training, leveraging both global and local coherence to select high-quality candidates and assign weights to prioritize haze-free regions. We verify the effectiveness of our method, with experiments demonstrating that it achieves state-of-the-art performance on RID tasks. Code will be available at https://github.com/cnyvfang/CORUN-Colabator.