Remote Sensing Image Dehazing: A Systematic Review of Progress, Challenges, and Prospects

For the purposes of this review, we adopt an inclusive definition of “dehazing” that encompasses all methodologies designed to mitigate the effects of fog, haze, and optically cloud layers. In this review, we have systematically examined over 200 papers 📜📜📜, summarizing and analyzing more than 100 Remote Sensing Image Dehazing methods.

😻 If this work is helpful for you, please help star this repo. Thanks!

📣 News

• 2025/12/15: Added 1 TGRS 2025 paper, 1 JSTARS 2025 paper
• 2025/12/05: 🏆 More than 100 methods have been included !
• 2025/12/05: Added 1 ACM MM 2025 paper, 1 ICASSP 2025 paper, 2 JSTARS 2025 papers, 2 TGRS 2025 papers, 1 Remote Sensing 2020 paper, 1 IJCNN 2025 paper
• 2025/11/09: Added 2 datasets: HyperDehazing, RRSHID.
• 2025/10/25: Added a Reproducibility Checklist.
• 2025/08/29: Added 2 TGRS 2025 papers, 1 TGRS 2024 paper.
• 2025/07/26: Added 2 JSTARS 2025 papers, 1 GRSL 2025 paper.
• 2025/07/22: Added 3 TGRS 2025 papers, 1 EAAI 2025 paper, 1 ISPRS P&RS 2024 paper and 1 Signal Processing 2025 paper.
• 2025/06/28: Paper submitted.
• 2025/05/15: Added 2 CVPR 2025 papers.

🍕 Introduction

Remote sensing images (RSIs) are frequently degraded by haze, fog, and thin clouds, which obscure surface reflectance and hinder downstream applications. This study presents the first systematic and unified survey of RSIs dehazing, integrating methodological evolution, benchmark assessment, and physical consistency analysis. We categorize existing approaches into a three-stage progression: from handcrafted physical priors, to data-driven deep restoration, and finally to hybrid physical-intelligent generation, and summarize more than 30 representative methods across CNNs, GANs, Transformers, and diffusion models. To provide a reliable empirical reference, we conduct large-scale quantitative experiments on five public datasets using 12 metrics, including PSNR, SSIM, CIEDE, LPIPS, FID, SAM, ERGAS, UIQI, QNR, NIQE, and HIST. Cross-domain comparison reveals that recent Transformer and diffusion-based models improve SSIM by 12%–18% and reduce perceptual errors by 20%–35% on average, while hybrid physics-guided designs achieve higher radiometric stability. A dedicated physical radiometric consistency experiment further demonstrates that models with explicit transmission or air light constraints reduce color bias by up to 27%. Based on these findings, we summarize open challenges: dynamic atmospheric modeling, multimodal fusion, lightweight deployment, data scarcity, and joint degradation, and outline promising research directions for future development of trustworthy, controllable, and efficient (TCE) dehazing systems. In addition, we discuss key technical challenges in Fig.2, such as dynamic atmospheric modeling, multi-modal data fusion, lightweight model design, data scarcity, and joint degradation scenarios, and propose future research directions.

Fig 1. Taxonomy of Remote Sensing Image Dehazing Methods.

Content:

0. Remote Sensing Image Datasets
1. Traditional Remote Sensing Image Restoration Methods
2. Deep Convolution for Remote Sensing Image Dehazing
3. Adversarial Generation for Remote Sensing Image Dehazing
4. Vision Transformer for Remote Sensing Image Dehazing
5. Diffusion Generation for Remote Sensing Image Dehazing
6. Current Challenges and Future Prospects
7. Evaluation

---

📂 Remote Sensing Image Datasets:

No.	Dataset	Year	Pub.	Number	Image Size	Types	Download
01	RICE	2019	arXiv	1236	512×512	Real	link
02	SateHaze1k	2020	WACV	400*3	512×512	Synthetic	link
03	LHID	2022	TGRS	31017	512×512	Synthetic	link
04	DHID	2022	TGRS	14990	512×512	Synthetic	link
05	RS-Haze	2023	TIP	51300	512×512	Synthetic	link
06	RSID	2023	TGRS	1000	256×256	Synthetic	link
07	HN-Snowy	2022	ISPRS P&RS	1237	256×256	Synthetic	link
08	CUHK-CR	2024	TGRS	1227	512×512	Synthetic	link
09	HyperDehazing	2024	ISPRS P&RS	2140	512×512	Real,Synthetic	link
10	RRSHID	2025	TGRS	3053	256×256	real	link

---

1. Traditional Image Enhancement and Physics Model for Remote Sensing Image Dehazing:

🚀🚀🚀Update (in 2025-12-15) 🎈

No.	Year	Model	Pub.	Title	Links
01	2015	DHIM	SPL	Haze removal for a single remote sensing image based on deformed haze imaging model	Paper/[Project]
02	2017	GRS-HTM	Signal Processing	Haze removal for a single visible remote sensing image	Paper/[Project]
03	2018	HMF	GRSL	A Framework for Outdoor RGB Image Enhancement and Dehazing	Paper/[Project]
04	2018	SMIDCP	GRSL	Haze and thin cloud removal via sphere model improved dark channel prior	Paper/[Project]
05	2019	AHE	APCC	Single Image Dehazing Based on Adaptive Histogram Equalization and Linearization of Gamma Correction	Paper/[Project]
06	2019	DADN	Remote Sensing	Single Remote Sensing Image Dehazing Using a Prior-Based Dense Attentive Network	Paper/[Project]
07	2019	IDeRs	Information Sciences	IDeRs: Iterative dehazing method for single remote sensing image	Paper/[Project]
08	2020	CR-GAN-PM	ISPRS P&RS	Thin cloud removal in optical remote sensing images based on generative adversarial networks and physical model of cloud distortion	Paper/Project
09	2021	HID	TGRS	Fog Model-Based Hyperspectral Image Defogging	Paper/[Project]
10	2021	MDCP	GRSL	A novel thin cloud removal method based on multiscale dark channel prior	Paper/[Project]
11	2022	CLAHEMSF	MTA	Single image haze removal using contrast limited adaptive histogram equalization based multiscale fusion technique	Paper/[Project]
12	2022	GPD-Net	GRSL	Single Remote Sensing Image Dehazing Using Gaussian and Physics-Guided Process	Paper/[Project]
13	2022	EVPM	Information Sciences	Local patchwise minimal and maximal values prior for single optical remote sensing image dehazing	Paper/[Project]
14	2023	SGPLM	GRSL	UAV Image Haze Removal Based on Saliency- Guided Parallel Learning Mechanism	Paper/[Project]
15	2023	ED	JSTARS	Efficient Dehazing Method for Outdoor and Remote Sensing Images	Paper/[Project]
16	2023	SRD	Remote Sensing	Remote Sensing Image Haze Removal Based on Superpixel	Paper/[Project]
17	2023	RLDP	Remote Sensing	Single Remote Sensing Image Dehazing Using Robust Light-Dark Prior	Paper/[Project]
18	2023	HALP	TGRS	Remote Sensing Image Dehazing Using Heterogeneous Atmospheric Light Prior	Paper/Project
19	2024	ALFE	TGRS	A Remote Sensing Image Dehazing Method Based on Heterogeneous Priors	Paper/[Project]

---

2. Deep Convolution for Remote Sensing Image Dehazing:

🚀🚀🚀Update (in 2025-12-15) 🎈

No.	Year	Model	Pub.	Title	Links
01	2016	MSDN	ECCV	Single image dehazing via multi-scale convolutional neural networks	Paper/[Project]
02	2019	RSC-Net	ISPRS P&RS	Thin cloud removal with residual symmetrical concatenation network	Paper/[Project]
03	2020	RSDehazeNet	TGRS	RSDehazeNet: Dehazing network with channel refinement for multispectral remote sensing images	Paper/Project
04	2020	FCTF-Net	GRSL	A coarse-to-fine two-stage attentive network for haze removal of remote sensing images	Paper/Project
05	2020	UCR	TGRS	Single image cloud removal using U-Net and generative adversarial networks	Paper/[Project]
06	2020	DSen2-CR	ISPRS P&RS	Cloud removal in Sentinel-2 imagery using a deep residual neural network and SAR-optical data fusion	Paper/[Project]
07	2021	CNNIM	JSTARS	Thin cloud removal for multispectral remote sensing images using convolutional neural networks combined with an imaging model	Paper/[Project]
08	2022	DCIL	TGRS	Dense haze removal based on dynamic collaborative inference learning for remote sensing images	Paper/Project
09	2022	SG-Net	ISPRS P&RS	A spectral grouping-based deep learning model for haze removal of hyperspectral images	Paper/Project
10	2022	GLF-CR	ISPRS P&RS	GLF-CR: SAR-enhanced cloud removal with global–local fusion	Paper/Project
11	2022	MBG-CR	ISPRS P&RS	Semi-supervised thin cloud removal with mutually beneficial guides	Paper/[Project]
12	2022	NE module	CVPRW	Nonuniformly Dehaze Network for Visible Remote Sensing Images	Paper/[Project]
13	2023	MSDA-CR	GRSL	Cloud removal in optical remote sensing imagery using multiscale distortion-aware networks	Paper/[Project]
14	2023	EMPF-Net	TGRS	Encoder-free multiaxis physics-aware fusion network for remote sensing image dehazing	Paper/Project
15	2023	PSMB-Net	TGRS	Partial siamese with multiscale bi-codec networks for remote sensing image haze removal	Paper/Project
16	2023	HS2P	Information Fusion	HS2P: Hierarchical spectral and structure-preserving fusion network for multimodal remote sensing image cloud and shadow removal	Paper/Project
17	2023	CP-FFCN	ISPRS P&RS	Blind single-image-based thin cloud removal using a cloud perception integrated fast Fourier convolutional network	Paper/[Project]
18	2023	GHRN	JAG	Incorporating inconsistent auxiliary images in haze removal of very high resolution images	Paper/[Project]
19	2024	SFAN	TGRS	Spatial-frequency adaptive remote sensing image dehazing with mixture of experts	Paper/Project
20	2024	EDED-Net	Remote Sensing	End-to-end detail-enhanced dehazing network for remote sensing images	Paper/[Project]
21	2024	ConvIR	TPAMI	Revitalizing Convolutional Network for Image Restoration	Paper/Project
22	2024	PhDnet	Information Fusion	PhDnet: A novel physic-aware dehazing network for remote sensing images	Paper/Project
23	2024	HyperDehazeNet	ISPRS P&RS	HyperDehazing: A hyperspectral image dehazing benchmark dataset and a deep learning model for haze removal	Paper/[Project]
24	2024	HDRSA-Net	ISPRS P&RS	HDRSA-Net: Hybrid dynamic residual self-attention network for SAR-assisted optical image cloud and shadow removal	Paper/Project
25	2024	ICL-Net	JSTARS	ICL-Net: Inverse cognitive learning network for remote sensing image dehazing	Paper/[Project]
26	2024	C2AIR	WACV	C2AIR: Consolidated Compact Aerial Image Haze Removal	Paper/Project
27	2024	AU-Net	TGRS	Dehazing Network: Asymmetric Unet Based on Physical Model	Paper/Project
28	2025	BMFH-Net	TCSVT	Bidirectional-Modulation Frequency-Heterogeneous Network for Remote Sensing Image Dehazing	Paper/Project
29	2025	HPN-CR	TGRS	HPN-CR: Heterogeneous Parallel Network for SAR-Optical Data Fusion Cloud Removal	Paper/Project
30	2025	DDIA-CFR	Information Fusion	Breaking through clouds: A hierarchical fusion network empowered by dual-domain cross-modality interactive attention for cloud-free image reconstruction	Paper/[Project]
31	2025	SMDCNet	ISPRS P&RS	Cloud removal with optical and SAR imagery via multimodal similarity attention	Paper/[Project]
32	2025	MIMJT	ECCV	Satellite Image Dehazing Via Masked Image Modeling and Jigsaw Transformation	Paper/[Project]
33	2025	MCAF-Net	TGRS	Real-World Remote Sensing Image Dehazing: Benchmark and Baseline	Paper/Project
34	2025	DFDNet	JSTARS	Density-Guided and Frequency Modulation Dehazing Network for Remote Sensing Images	Paper/[Project]
35	2025	CCHD	GRSL	CCHD: Chain Connection and Hybrid Dense Attention for Remote Sensing Dehazing	Paper/[Project]
36	2025	CLIP-HNet	ACM MM	CLIP-HNet: Hybrid Network with Cross-Modal Guidance for Self-Supervised Remote Sensing Dehazing	Paper/[Project]
37	2025	HazeCLIP	ICASSP	HazeCLIP: Towards Language Guided Real-World Image Dehazing	Paper/Project
38	2025	DR3DF-Net	TGRS	Dynamic-Routing 3D-Fusion Network for Remote Sensing Image Haze Removal	Paper/Project
39	2025	SFRDP-Net	TGRS	Spatial–Frequency Residual-Guided Dynamic Perceptual Network for Remote Sensing Image Haze Removal	Paper/Project
40	2025	MiDUNet	TGRS	MiDUNet: Model Inspired Deep Unfolding Network for Non-homogeneous Image Dehazing	Paper/[Project]

---

3. Adversarial Generation for Remote Sensing Image Dehazing:

🚀🚀🚀Update (in 2025-12-15) 🎈

No.	Year	Model	Pub.	Title	Links
01	2018	Cloud-GAN	IGARSS	Cloud-gan: Cloud removal for sentinel-2 imagery using a cyclic consistent generative adversarial networks	Paper/[Project]
02	2020	CR-GAN-PM	ISPRS P&RS	Thin cloud removal in optical remote sensing images based on generative adversarial networks and physical model of cloud distortion	Paper/Project
03	2020	UCR	TGRS	Single image cloud removal using U-Net and generative adversarial networks	Paper/[Project]
04	2020	SpA-GAN	arXiv	Cloud Removal for Remote Sensing Imagery via Spatial Attention Generative Adversarial Network	Paper/Project
05	2020	FCTF-Net	GRSL	A coarse-to-fine two-stage attentive network for haze removal of remote sensing images	Paper/Project
06	2020	SScGAN	WACV	Single Satellite Optical Imagery Dehazing using SAR Image Prior Based on conditional Generative Adversarial Networks	Paper/[Project]
07	2020	ES-CCGAN	Remote Sensing	Unsupervised Haze Removal for High-Resolution Optical Remote-Sensing Images Based on Improved Generative Adversarial Networks	Paper/[Project]
08	2021	SAR2Opt-GAN-CR	TGRS	Cloud removal in remote sensing images using generative adversarial networks and SAR-to-optical image translation	Paper/[Project]
09	2021	SkyGAN	WACV	Domain-Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing	Paper/[Project]
10	2022	Dehaze-AGGAN	TGRS	Dehaze-AGGAN: Unpaired remote sensing image dehazing using enhanced attention-guide generative adversarial networks	Paper/[Project]
11	2023	MSDA-CR	GRSL	Cloud removal in optical remote sensing imagery using multiscale distortion-aware networks	Paper/[Project]
12	2024	TC-BC	ISPRS P&RS	A thin cloud blind correction method coupling a physical model with unsupervised deep learning for remote sensing imagery	Paper/Project
13	2025	MT_GAN	ISPRS P&RS	MT_GAN: A SAR-to-optical image translation method for cloud removal	Paper/Project
14	2025	UTCR-Dehaze	EAAI	UTCR-Dehaze: U-Net and transformer-based cycle-consistent generative adversarial network for unpaired remote sensing image dehazing	Paper/[Project]
15	2025	Dehazing-DiffGAN	TGRS	Dehazing-DiffGAN: Sequential Fusion of Diffusion Models and GANs for High-Fidelity Remote Sensing Image Dehazing	Paper/Project
16	2025	DAH-TrafficRSNet	JSTARS	DAH-TrafficRSNet: Dual-Branch Traffic Remote Sensing Image Dehazing Network Based on Atmospheric Scattering Model and Hierarchical Feature Interaction	Paper/[Project]

---

4. Vision Transformer for Remote Sensing Image Dehazing:

🚀🚀🚀Update (in 2025-12-15) 🎈

No.	Year	Model	Pub.	Title	Links
01	2022	TransRA	Multidimensional Systems and Signal Processing	TransRA: Transformer and residual attention fusion for single remote sensing image dehazing	Paper/[Project]
02	2023	DehazeFormer	TIP	Vision transformers for single image dehazing	Paper/Project
03	2023	FormerCR	Remote Sensing	Former-CR: A transformer-based thick cloud removal method with optical and SAR imagery	Paper/[Project]
04	2023	RSDformer	GRSL	Learning an Effective Transformer for Remote Sensing Satellite Image Dehazing	Paper/Project
05	2023	Trinity-Net	TGRS	Trinity-Net: Gradient-guided Swin transformer-based remote sensing image dehazing and beyond	Paper/Project
06	2023	AIDTransformer	WACV	Aerial Image Dehazing with Attentive Deformable Transformers	Paper/Project
07	2024	DCR-GLFT	TGRS	Density-aware Cloud Removal of Remote Sensing Imagery Using a Global-Local Fusion Transformer	Paper/[Project]
08	2024	SSGT	JSTARS	SSGT: Spatio-Spectral Guided Transformer for Hyperspectral Image Fusion Joint with Cloud Removal	Paper/[Project]
09	2024	PGSformer	GRSL	Prompt-Guided Sparse Transformer for Remote Sensing Image Dehazing	Paper/[Project]
10	2024	ASTA	GRSL	Additional Self-Attention Transformer With Adapter for Thick Haze Removal	Paper/Project
11	2024	Dehaze-TGGAN	TGRS	Dehaze-TGGAN: Transformer-Guide Generative Adversarial Networks With Spatial-Spectrum Attention for Unpaired Remote Sensing Dehazing	Paper/[Project]
12	2024	PCSformer	TGRS	Proxy and Cross-Stripes Integration Transformer for Remote Sensing Image Dehazing	Paper/Project
13	2025	DehazeXL	CVPR	Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images	Paper/Project
14	2025	DecloudFormer	Pattern Recognition	DecloudFormer: Quest the key to consistent thin cloud removal of wide-swath multi-spectral images	Paper/Project
15	2025	CINet	TGRS	Cross-Level Interaction and Intralevel Fusion Network for Remote Sensing Image Dehazing	Paper/[Project]
16	2025	MABDT	Signal Processing	MABDT: Multi-scale attention boosted deformable transformer for remote sensing image dehazing	Paper/Project
17	2025	CLEAR-Net	JSTARS	CLEAR-Net: A Cascaded Local and External Attention Network for Enhanced Dehazing of Remote Sensing Images	Paper/[Project]
18	2025	Winscaleformer	JSTARS	Winscaleformer: Diffusion-Attention-Based Single Remote Sensing Image Dehazing	Paper/Project
19	2025	Guidance Net	IJCNN	Guidance Net: Remote Sensing Image Dehazing with Guidance of Prompt Texture Information Embedding	Paper/[Project]
20	2025	DehazeMamba	JSTARS	DehazeMamba: SAR-Guided Optical Remote Sensing Image Dehazing With Adaptive State Space Model	Paper/[Project]

---

5. Diffusion Generation for Remote Sensing Image Dehazing:

🚀🚀🚀Update (in 2025-12-15) 🎈

No.	Year	Model	Pub.	Title	Links
01	2023	ARDD-Net	GRSL	Remote Sensing Image Dehazing Using Adaptive Region-Based Diffusion Models	Paper/[Project]
02	2023	SeqDMs	Remote Sensing	Cloud removal in remote sensing using sequential-based diffusion models	Paper/[Project]
03	2024	ADND-Net	GRSL	Diffusion Models Based Null-Space Learning for Remote Sensing Image Dehazing	Paper/[Project]
04	2024	RSHazeDiff	T-ITS	RSHazeDiff: A unified Fourier-aware diffusion model for remote sensing image dehazing	Paper/Project
05	2024	IDF-CR	TGRS	IDF-CR: Iterative diffusion process for divide-and-conquer cloud removal in remote-sensing images	Paper/Project
06	2025	EMRDM	CVPR	Effective Cloud Removal for Remote Sensing Images by an Improved Mean-Reverting Denoising Model with Elucidated Design Space	Paper/Project
07	2025	DFG-DDM	TGRS	DFG-DDM: Deep Frequency-Guided Denoising Diffusion Model for Remote Sensing Image Dehazing	Paper/Project
08	2025	DS-RDMPD	TGRS	A Dual-Stage Residual Diffusion Model with Perceptual Decoding for Remote Sensing Image Dehazing	Paper/Project

---

6. 🏄 Current Challenges and Future Prospects

Fig 2. Future prospects for RSI dehazing: Trustworthy, controllable, and efficient (TCE) remote sensing dehazing systems.

---

📊 Evaluation:

For evaluation on Dehazed results, modify 'test_original' and 'test_restored' to the corresponding path

python evaluate.py --train_folder [restored image path] --target_folder [ground-truth image path]

Make sure the file structure is consistent with the following:

dataset
├── Restored
│   ├── RICE
│   ├── RRSHID-M
│   ├── RRSHID-TK
│   ├── RRSHID-TN
│   ├── SH-M
│   ├── SH-TK
│   └── SH-TN
│       └── 1.png, 2.png, ...
|
├── Ground-truth
│   ├── RICE-GT
│   ├── RRSHID-M-GT
│   ├── RRSHID-TK-GT
│   ├── RRSHID-TN-GT
│   ├── SH-M-GT
│   ├── SH-TK-GT
│   └── SH-TN-GT
│       └── 1.png, 2.png, ...

Table 1. Quantitative performance at PSNR (dB) and SSIM of remote sensing image restoration algorithms evaluated on the SateHaze1k (SH-TN, SH-M, SH-TK) and RICE datasets.

Methods	Category	SH-TN		SH-M		SH-TK		RICE
		PSNR	SSIM	PSNR	SSIM	PSNR	SSIM	PSNR	SSIM
SMIDCP	Traditional	13.639	0.833	15.990	0.863	14.956	0.757	16.573	0.712
EVPM	Traditional	20.426	0.891	20.656	0.918	16.647	0.787	15.217	0.742
IeRs	Traditional	15.048	0.772	14.763	0.785	11.754	0.702	15.750	0.611
GRS-HTM	Traditional	15.489	0.762	15.071	0.784	10.473	0.462	18.278	0.825
SRD	Traditional	21.327	0.896	20.774	0.930	17.265	0.814	20.550	0.896
DHIM	Traditional	19.445	0.891	19.916	0.917	16.595	0.810	19.240	0.882
EMPF-Net	CNN	27.400	0.960	31.450	0.975	26.330	0.928	35.845	0.979
SFAN	CNN	23.688	0.963	28.191	0.977	23.006	0.942	35.374	0.941
ICL-Net	CNN	24.590	0.923	25.670	0.937	21.780	0.859	36.940	0.960
FCTF-Net	CNN	23.590	0.913	22.880	0.927	20.030	0.816	25.535	0.870
PSMB-Net	CNN	22.946	0.949	27.921	0.960	21.273	0.919	28.057	0.893
DCIL	CNN	20.187	0.947	27.431	0.964	21.450	0.926	27.720	0.876
EDED-Net	CNN	24.605	0.893	25.360	0.913	22.418	0.846	31.907	0.945
TransRA	Transformer	25.200	0.930	26.500	0.947	22.730	0.875	31.130	0.955
PGSformer	Transformer	25.534	0.918	26.622	0.933	23.596	0.863	34.404	0.948
Trinity-Net	Transformer	21.304	0.946	26.473	0.963	20.756	0.915	29.248	0.908
RSDformer	Transformer	24.210	0.912	26.241	0.934	23.011	0.853	33.013	0.953
ARDD-Net	Diffusion	26.840	0.926	26.470	0.932	26.830	0.932	-	-
ADND-Net	Diffusion	26.910	0.927	26.670	0.936	26.940	0.936	-	-
RSHazeDiff	Diffusion	-	-	-	-	-	-	36.560	0.958

---

Go to Reproducibility Checklist

---

📚 Citation:

• If you find [our survey paper] and evaluation code are useful, please cite the following paper:

@article{zhou2025remote,
  title={Remote Sensing Image Dehazing: A Systematic Review of Progress, Challenges, and Prospects},
  author={Zhou, Heng and Liu, Xiaoxiong and Zhang, Zhenxi and Yun, Jieheng and Li, Chengyang and Yang, Yunchu and Tian, Chunna and Wu, Xiao-Jun},
  journal={arXiv preprint arXiv:},
  pages={1--56},
  year={2025},
}

---

👏👏👏 Thanks to the above authors for their excellent work！