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

Heng Zhou; Xiaoxiong Liu; Zhenxi Zhang; Jieheng Yun; Chengyang Li; Yunchu Yang; Dongyi Xia; Chunna Tian

cs.CVMar 18, 2026

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

Authors: Heng Zhou, Xiaoxiong Liu, Zhenxi Zhang, Jieheng Yun, Chengyang Li, Yunchu Yang, Dongyi Xia, Chunna Tian,

Organizations: School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China · Josef Kittler Research Institute on Artificial Intelligence, Jiangnan University, Wuxi 214122, China · School of Electronic Engineering, Xidian University, Xi’an 710071, China · College of Artificial Intelligence, China University of Petroleum (Beijing), Beijing 102249, China ·

Abstract

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 airlight 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 degradations, and outline promising research directions for future development of trustworthy, controllable, and efficient (TCE) dehazing systems. All reviewed resources, including source code, benchmark datasets, evaluation metrics, and reproduction configurations are publicly available at https://github.com/VisionVerse/RemoteSensing-Restoration-Survey.

Figures & tables

Term	Physical Cause	Relation to This Review
Haze	Aerosol scattering and absorption veil surface radiance and reduce contrast.	Core focus . This survey fully covers haze as the primary visibility degradation.
Thin Cloud	Weak scattering by small droplets forms a semi-transparent layer.	Included . Treated as haze-like when optical thickness is low.
Thick Cloud, Cloud Shadows	Strong occlusion from dense clouds or shadows causes irreversible radiance loss.	Excluded . Belongs to cloud removal rather than dehazing.
Atmospheric Correction	Gas absorption and Rayleigh or Mie scattering alter top-of-atmosphere radiance.	Related but not covered . A radiometric calibration process rather than visibility restoration.

Table 1: The difference analysis of haze, thin clouds, discussed in this review, and thick clouds, atmospheric correction.

Figure 1: Illustrative scenarios for RSIs dehazing. Each column (a)–(d) shows a different land-cover type from riverine–agricultural to industrial–urban areas, with haze density increasing from light (a) to heavy (d).

Figure 3: Number of papers published in RSIs dehazing up to January 2026.

Publication	$\mathbf{IF_{2025}}$	h5	Num.
IEEE Trans. on Pattern Analysis and Machine Intelligence	18.6	196	6
Information Fusion	15.5	134	6
IEEE Trans. on Image Processing	13.7	150	16
ISPRS J. of Photogrammetry and Remote Sensing	12.2	104	12
IEEE Trans. on Circuits and Systems for Video Technology	11.1	94	11
IEEE Trans. on Geoscience and Remote Sensing	8.6	141	99

Table 2: Impact Factor (IF2025), h5-index, and Paper Count † of Selected Journals and Conferences.

Figure 4: The distribution ratio of high-quality journals (impact factor greater than 7) and conference articles in the past three years.

Figure 5: Diagram of Image Enhancement and Priors Modeling for RSIs Dehazing.

Figure 6: Diagram of Deep Convolution Methods for RSIs Dehazing.

Figure 7: Diagram of Adversarial Generation Methods for RSIs Dehazing.

Figure 8: Diagram of Vision Transformers Methods for RSIs Dehazing.

Figure 9: Diagram of Diffusion Generation Methods for RSIs Dehazing.

Method	Publication	Code Link
CR-GAN-PM [ 94 ]	ISPRS P&RS 2020	https://github.com/Neooolee/CR-GAN-PM
RSDehazeNet [ 50 ]	TGRS 2020	https://github.com/tianqiong123/RSDehazeNet
DCIL [ 219 ]	TGRS 2022	https://github.com/Shan-rs/DCI-Net
GLF-CR [ 199 ]	ISPRS P&RS 2022	https://github.com/xufangchn/GLF-CR
DehazeFormer [ 164 ]	TIP 2023	https://github.com/IDKiro/DehazeFormer
RSDformer [ 162 ]	GRSL 2023	https://github.com/MingTian99/RSDformer

Table 3: Selected publicly available codes for RSIs dehazing methods.

Datasets	Number	Real/Syn.	Sensor Type	$\boldsymbol{N}_{spectrum}$	Image Size	Application	Link
RICE1 19 [ 105 ]	500	Real	Google Earth	3	$512\times 512$	Hazy, Thin cloud	GitHub
RICE2 19 [ 105 ]	736	Real	Landsat 8 OLI/TIRS	3	$512\times 512$	Hazy, Thin cloud	GitHub
SateHaze1k 20 [ 66 ]	1200	Syn.	GF-2	3	$512\times 512$	Hazy	GitHub
LHID 22 [ 219 ]	31017	Syn.	Google Earth	3	$512\times 512$	Hazy	GitHub
DHID 22 [ 219 ]	14990	Syn.	Aerial Camera	3	$512\times 512$	Hazy	GitHub
RS-HAZE 23 [ 164 ]	51300	Syn.	Landsat 8 OLI/TIRS	11	$512\times 512$	Hazy	GitHub

Table 4: Summary of representative remote-sensing haze datasets, including data scale, real/synthetic type, sensor source, spectral counts, resolution, and applications.

Methods	Pub.	Overview	Advantages	Limitations
SMIDCP [ 93 ]	GRSL 2018	A sphere model to improve the DCP and combining it with HF for image enhancement.	Strong capability in handling inhomogeneous conditions, dense haze, and thin clouds.	Limited adaptability to extreme scenarios.
MDCP [ 156 ]	GRSL 2021	Integrate DCP into the multiscale transform and process images by selecting appropriate fusion rules and an optimized Laplacian model.	Effectively removes thin clouds and supports multi-temporal reference images.	Long processing time and highly dependent on the quality of reference images.
RSC-Net [ 96 ]	ISPRS P&RS 2019	Employs the encoding-decoding framework to enable end-to-end thin cloud removal.	Symmetrical concatenation effectively preserves details of cloud-free regions.	Relies on specific sensor band configurations and lacks validation of adaptability to complex atmospheric conditions.
RSDehazeNet [ 50 ]	TGRS 2020	An end-to-end network combining channel attention mechanism and global residual learning.	Fast processing speed, preserves image details, and high realism of synthetic data.	The inadequate adaptability to extreme conditions or complex terrain.
FCTF [ 99 ]	GRSL 2020	Adopting a coarse-to-fine two-stage architecture to refine dehazing results and optimize image details.	Improvement in dehazing accuracy under complex scenes.	Insufficient generalization capability to complex haze distributions and diverse ground surface characteristics.
CNNIM [ 246 ]	JSTARS 2021	Utilizing U-Net and Slope-Net to subtract the thin cloud thickness map and obtain a clear image.	Capable of acquiring thin cloud information at different altitudes and for each band.	Exhibits significant cumulative estimation errors for real-world images.

Table 5: Summary of representative remote sensing image dehazing methods, including publication venues, core designs, technical advantages, and existing limitations.

Methods	Category	SH-TN		SH-M		SH-TK		RICE
Methods	Category	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$
DHIM 15 [ 137 ]	Traditional	19.445	0.891	19.916	0.917	16.595	0.810	19.240	0.882
GRS-HTM 17 [ 110 ]	Traditional	15.489	0.762	15.071	0.784	10.473	0.462	18.278	0.825
SMIDCP 18 [ 93 ]	Traditional	13.639	0.833	15.990	0.863	14.956	0.757	16.573	0.712
IDeRs 19 [ 205 ]	Traditional	15.048	0.772	14.763	0.785	11.754	0.702	15.750	0.611
EVPM 22 [ 53 ]	Traditional	20.426	0.891	20.656	0.918	16.647	0.787	15.217	0.742

Table 6: Quantitative performance at PSNR (dB) and SSIM of RSIs dehazing algorithms evaluated on the SateHaze1k and RICE datasets. Red and blue values indicate the best and second-best performance for each metric, respectively.

Metrics	SpA-GAN [ 134 ]	DCIL [ 219 ]	DehazeFormer [ 164 ]	PSMB-Net [ 167 ]	Trinity-Net [ 20 ]	LFD-Net [ 75 ]	ASTA [ 7 ]	DehazeXL [ 13 ]
ERGAS $\downarrow$	13.386	14.473	18.127	13.075	22.765	23.813	12.188	26.444
	32.128	30.591	29.493	28.706	34.624	34.873	11.727	37.214
	24.088	17.574	16.013	16.808	22.293	25.929	15.343	36.951
UIQI $\uparrow$	0.902	0.904	0.889	0.911	0.650	0.858	0.913	0.759
	0.555	0.621	0.624	0.624	0.425	0.598	0.944	0.428
	0.739	0.843	0.837	0.841	0.650	0.773	0.845	0.544

Table 7: Quantitative performance at SAM, ERGAS, UIQI, QNR. NIQE and HIST on the SateHaze1k datasets. Red and blue values indicate the best and second-best performance for each metric, respectively.

Methods	Category	LHID					DHID
Methods	Category	CIEDE $\downarrow$	LPIPS $\downarrow$	FID $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	CIEDE $\downarrow$	LPIPS $\downarrow$	FID $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$
DCP 10 [ 55 ]	Traditional	9.161	0.481	21.490	21.120	0.818	9.867	0.163	79.920	18.920	0.824
IDeRs 19 [ 205 ]	Traditional	19.563	0.633	44.650	14.680	0.627	19.942	0.344	120.17	13.330	0.575
FCTF-Net 20 [ 99 ]	CNN	5.423	0.459	21.210	25.850	0.876	12.794	0.221	128.490	17.210	0.739
DCIL 22 [ 219 ]	CNN	5.180	0.447	14.930	28.120	0.898	4.877	0.131	64.730	26.950	0.896
PSMB-Net 23 [ 167 ]	CNN	5.864	0.454	16.130	28.890	0.900	4.965	0.113	53.830	27.070	0.887

Table 8: Quantitative performance at CIEDE (

\downarrow

), LPIPS (

\downarrow

), FID (

\downarrow

) PSNR (

\uparrow

) and SSIM (

\uparrow

) of SOTA methods evaluated on the LHID and DHID datasets. Red and blue values indicate the best and second-best performance for each metric, respectively.

Figure 10: Quantitative comparison of PSNR (dB) across eight SOTA dehazing models on SateHaze1k (SH) and RRSIHID. The error bars indicate performance variance.

Methods	PSNR	FLOPs(G)	FPS	#Param(M)
SpA-GAN 20 [ 134 ]	19.664	67.931	29.84	0.210
DCIL 22 [ 219 ]	22.641	107.445	52.35	26.509
DehazeFormer 23 [ 164 ]	22.624	24.817	41.48	0.686
PSMB-Net 23 [ 167 ]	23.953	392.754	18.54	12.488
Trinity-Net 23 [ 20 ]	23.723	123.889	14.40	20.139
LFD-Net 23 [ 75 ]	17.975	23.352	269.07	0.090

Table 9: Model efficiency and performance comparison on SateHaze1k datasets.

Figure 11: Comparison of representative RSIs dehazing methods in terms of dehazing accuracy (PSNR) and computational complexity (FLOPs and Parameter).

Figure 12: Radiometric consistency analysis of RSIs before and after dehazing.

Methods	SH-TN		SH-M		SH-TK
Methods	SAM $\downarrow$	ERGAS $\downarrow$	SAM $\downarrow$	ERGAS $\downarrow$	SAM $\downarrow$	ERGAS $\downarrow$
SpA-GAN [ 134 ]	2.670	13.386	4.246	32.128	3.725	24.088
DCIL [ 219 ]	2.462	14.473	4.304	30.591	2.816	17.574
DehazeFormer [ 164 ]	2.646	18.127	3.923	29.493	3.032	16.013
PSMB-Net [ 167 ]	2.980	13.075	3.565	28.706	3.440	16.808
Trinity-Net [ 20 ]	2.835	22.765	3.457	34.624	3.494	22.293

Table 10: Physical consistency comparison in terms of SAM and ERGAS on SateHaze1k.

Figure 13: Visual comparison of dehazing results on the SateHaze1k datasets.

Figure 14: Visual comparison of dehazing results on the RICE datasets.

Figure 15: Visual comparison of dehazing results on the RRSHID datasets.

Figure 16: Uncertainty maps of DehazeXL on the RRSHID-TN, RRSHID-M and SateHaze1k-M datasets.

Metrics	SpA-GAN [ 134 ]	DCIL [ 219 ]	DehazeFormer [ 164 ]	PSMB-Net [ 167 ]	Trinity-Net [ 20 ]	LFD-Net [ 75 ]	ASTA [ 7 ]	DehazeXL [ 13 ]
PSNR $\uparrow$	20.640	20.846	22.640	23.190	23.003	21.002	22.420	22.980
	20.525	23.254	23.360	23.120	22.767	20.838	20.843	23.023
	20.947	24.640	24.550	25.180	24.055	20.433	24.160	24.171
SSIM $\uparrow$	0.493	0.527	0.594	0.643	0.631	0.517	0.591	0.592
	0.506	0.651	0.660	0.657	0.665	0.544	0.651	0.640
	0.573	0.707	0.705	0.726	0.725	0.527	0.699	0.681

Table 11: Quantitative evaluation on the authentic RRSHID datasets.

Figure 17: SSIM curves of different methods on SateHaze1k and RRSHID (thin to thick haze), reflecting structural fidelity under varying haze conditions.

Models	PSNR $\uparrow$	SSIM $\uparrow$	CIEDE $\downarrow$	LPIPS $\downarrow$	FID $\downarrow$	SAM $\downarrow$	ERGAS $\downarrow$	UIQI $\uparrow$	QNR $\uparrow$	NIQE $\downarrow$	HIST $\uparrow$
SpA-GAN [ 134 ]	20.956	0.762	9.141	0.336	88.895	5.526	42.712	0.762	0.453	2.342	0.311
DCIL [ 219 ]	18.762	0.725	11.124	0.351	87.667	6.287	63.187	0.725	0.418	1.749	0.297
DehazeFormer [ 164 ]	20.842	0.736	9.336	0.325	83.375	5.166	43.439	0.736	0.467	1.056	0.314
PSMB-Net [ 167 ]	13.161	0.569	23.019	0.569	132.442	10.735	121.745	0.569	0.229	1.172	0.235
Trinity-Net [ 20 ]	12.884	0.410	26.921	0.739	83.749	7.414	44.230	0.693	0.413	0.977	0.170
LFD-Net [ 75 ]	13.695	0.618	27.638	0.441	117.951	7.848	183.025	0.618	0.322	1.529	0.257

Table 12: Cross-domain evaluation: SateHaze1k

\rightarrow

RICE.

Models	PSNR $\uparrow$	SSIM $\uparrow$	CIEDE $\downarrow$	LPIPS $\downarrow$	FID $\downarrow$	SAM $\downarrow$	ERGAS $\downarrow$	UIQI $\uparrow$	QNR $\uparrow$	NIQE $\downarrow$	HIST $\uparrow$
SpA-GAN [ 134 ]	11.971	0.337	24.913	0.526	201.851	10.506	153.132	0.337	0.101	1.210	0.144
DCIL [ 219 ]	10.847	0.344	27.813	0.564	210.276	9.816	174.042	0.343	0.096	1.174	0.094
DehazeFormer [ 164 ]	12.490	0.352	23.755	0.537	207.182	10.259	144.739	0.337	0.113	1.957	0.142
PSMB-Net [ 167 ]	11.690	0.324	26.372	0.460	151.500	8.545	159.266	0.324	0.118	1.032	0.227
Trinity-Net [ 20 ]	15.620	0.446	17.703	0.448	169.603	10.564	101.522	0.427	0.159	1.148	0.319
LFD-Net [ 75 ]	10.761	0.279	33.477	0.811	274.743	29.765	172.186	0.279	0.014	0.961	0.197

Table 13: Cross-domain evaluation: SateHaze1k

\to

RRSHID.

Models	PSNR $\uparrow$	SSIM $\uparrow$	CIEDE $\downarrow$	LPIPS $\downarrow$	FID $\downarrow$	SAM $\downarrow$	ERGAS $\downarrow$	UIQI $\uparrow$	QNR $\uparrow$	NIQE $\downarrow$	HIST $\uparrow$
SpA-GAN [ 134 ]	17.088	0.806	15.290	0.286	62.415	8.687	28.157	0.806	0.329	1.128	0.760
DCIL [ 219 ]	19.244	0.804	9.119	0.204	22.702	3.227	22.186	0.804	0.589	0.765	0.736
DehazeFormer [ 164 ]	19.661	0.873	8.322	0.122	21.810	3.099	21.407	0.873	0.601	1.187	0.754
PSMB-Net [ 167 ]	18.566	0.831	10.745	0.176	22.051	4.401	23.809	0.831	0.516	0.917	0.748
Trinity-Net [ 20 ]	18.767	0.693	9.117	0.487	25.253	3.872	23.059	0.693	0.549	0.921	0.762
LFD-Net [ 75 ]	16.032	0.765	14.063	0.261	51.687	7.119	31.573	0.765	0.365	1.018	0.709

Table 14: Cross-domain evaluation: SateHaze1k

\rightarrow

UAV-HAZE.

Figure 18: Cross-domain few-shot analysis of synthetic-real remote sensing dehazing datasets

Figure 19: Some failure cases on RRSHID (1-3 rows) and SateHaze1k (4-5 rows) datasets.

Methods	Publication	PSNR $\uparrow$	SSIM $\uparrow$	UIQI $\uparrow$	SAM $\downarrow$
DCP [ 55 ]	CVPR, 2009	26.292	0.781	0.691	0.182
AOD-Net [ 88 ]	ICCV, 2017	18.010	0.861	0.733	–
FFANet [ 141 ]	AAAI, 2020	30.891	0.898	0.944	0.090
NHRN [ 194 ]	TIP, 2021	26.140	0.823	0.886	–
Defog [ 79 ]	TGRS, 2022	24.323	0.642	0.592	0.421
SGNet [ 123 ]	ISPRS P&RS, 2022	34.720	0.947	0.965	0.077

Table 15: HSI dehazing results on the HyperDehazing datasets.

Figure 20: Visual comparison of dehazing results on the HyperDehazing datasets.

Methods	PSNR $\uparrow$	SSIM $\uparrow$	Trained on Clear Images		Trained on Dehazing Images
Methods	PSNR $\uparrow$	SSIM $\uparrow$	[email protected] $\uparrow$	mAP@[0.5:0.95] $\uparrow$	[email protected] $\uparrow$	mAP@[0.5:0.95] $\uparrow$
Faster RCNN [ 146 ]	–	–	55.4	39.5	68.0	48.1
+ SpA-GAN [ 134 ]	14.95	0.735	47.3 -8.1	33.2 -6.3	63.1 -4.9	43.6 -4.5
+ DCIL [ 219 ]	16.03	0.772	56.2 +0.8	39.8 +0.3	67.7 -0.3	47.8 -0.3
+ DehazeFormer [ 164 ]	23.27	0.886	61.6 +6.2	44.0 +4.5	68.6 +0.6	48.5 +0.4
+ PSMB-Net [ 167 ]	15.37	0.806	65.0 +9.6	45.2 +5.7	68.9 +0.9	48.6 +0.5

Table 16: Task-driven evaluation of detection-friendly dehazing on the HazyDet datasets.

Figure 21: Visual comparison of detection-friendly dehazing on the HazyDet datasets.

Methods	PSNR $\uparrow$	SSIM $\uparrow$	Trained on Clear Images			Trained on Dehazing Images
Methods	PSNR $\uparrow$	SSIM $\uparrow$	mIoU $\uparrow$	Acc $\uparrow$	F 1 -score $\uparrow$	mIoU $\uparrow$	Acc $\uparrow$	F 1 -score $\uparrow$
U-Net [ 149 ]	–	–	14.87	70.03	24.64	30.95	80.14	43.98
+ SpA-GAN [ 134 ]	13.45	0.639	13.65 -1.22	68.43 -1.60	23.06 -1.58	13.62 -17.33	74.17 -5.97	21.54 -22.44
+ DCIL [ 219 ]	13.60	0.680	18.17 +3.30	73.05 +3.02	29.41 +4.77	31.42 +0.47	80.05 -0.09	45.08 +1.10
+ DehazeFormer [ 164 ]	21.02	0.872	30.39 +15.52	80.77 +10.74	43.42 +18.78	36.18 +5.23	82.83 +2.69	49.95 +5.97
+ PSMB-Net [ 167 ]	13.14	0.752	17.72 +2.85	73.60 +3.57	29.07 +4.43	26.76 +4.19	77.98 +2.16	40.33 +3.65

Table 17: Task-driven evaluation of segmentation-friendly dehazing on the HazyUDD datasets.

Figure 22: Visual comparison of segmentation-friendly dehazing on the HazyUDD datasets.

Figure 23: Future prospects for RSIs dehazing: Trustworthy, controllable, and efficient (TCE) remote sensing dehazing system.

Dimension	Concrete Research Actions	Clear and Measurable Goals
Trustworthy	• Reliable parameter estimation based on differential equations, including transmittance, atmospheric light, and scattering intensity; • Radiation-consistency regularization via knowledge distillation; • Uncertainty modeling for extreme haze regions using depth estimation.	• Accuracy and stability of estimated physical variables across datasets and haze levels; • Radiometric metrics: SAM $\downarrow$ , ERGAS $\downarrow$ , QNR $\uparrow$ , HIST $\uparrow$ ; • Reduced color bias and spectral distortion under real-world conditions.
Controllable	• Physics-aware latent disentanglement separating shared physical factors and modality-private appearance; • Cross-modal semantic anchoring using high-level prior knowledge from large multimodal models such as CLIP; • Hierarchical and region-adaptive multimodal alignment based on segmenting anything model; • Self-supervised learning and test-time adaptation guided by SAR geometric location cues.	• Performance decay rate under cross-dataset and cross-sensor transfer; • Semantic consistency when modalities are added, removed, or substituted; • Cross-domain invariance of estimated physical variables under similar atmospheric conditions.
Efficient	• Lightweight Mamba architectures reducing redundant feature learning; • Parameter-efficient multimodal fusion via reparameterization; • Efficient diffusion-generative models with reduced inference steps; • Hardware-aware operator optimization for edge deployment.	• Model size, FLOPs, and inference latency; • Scalability to large-scale or wide-swath RS imagery; • Performance–efficiency trade-off (accuracy/physical consistency per computation cost).

Table 18: TCE framework with concrete research actions and measurable goals.

Image Dehazing

Image dehazing restores clear scene details and colors from images obscured by haze, fog, or smoke.

See all 35 papers

DPSF-Net: A Dual-Prior Spatial-Frequency Network for Real-World Remote Sensing Image Dehazing
Sep 7, 2026Mei Lu, Shangliang Shao, Shanliang YaoImage Dehazing Physics-Guided Image Restoration
School of Software Engineering, Jinling Institute of Technology, Nanjing 211100, China · School of Information Engineering, Yancheng Institute of Technology, Yancheng 224051, China
RTE-FM-Dehazer: Radiative Transfer Equation Inspired Flow Matching for Real-World Image Dehazing
Jul 2, 2026Chenfeng Wei, Chun Wang, Boyang Zhao +3Flow Matching Radiative Transfer
Xi’an Jiaotong-Liverpool University, China · University of Liverpool, UK · Mashang Consumer Finance Co. Ltd, China +3
HNDiff: Haze-Noise Diffusion for Image Dehazing
Aug 11, 2026Jin-Ting He, Fu-Jen Tsai, Yan-Tsung Peng +3Physics-Informed Diffusion Models Diffusion Models for Image Restoration
Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan · National Tsing Hua University, Taiwan · National Chengchi University, Taiwan +1

Sep 7, 2026J/K move · Enter open · S save

DPSF-Net: A Dual-Prior Spatial-Frequency Network for Real-World Remote Sensing Image Dehazing

Mei Lu, Shangliang Shao, Shanliang Yao

School of Software Engineering, Jinling Institute of Technology, Nanjing 211100, China · School of Information Engineering, Yancheng Institute of Technology, Yancheng 224051, China

Image Dehazing Physics-Guided Image Restoration

Open paper AskPDF arXiv

Real-world remote sensing image dehazing (RSID) remains challenging because atmospheric scattering, spatially non-uniform haze and colour distortion jointly degrade structural and spectral information. Most deep learning methods rely on RGB inputs and spatial-domain feature extraction, which limits their ability to separate global background haze from local surface details. Here, we propose DPSF-Net, a dual-prior spatial-frequency network built on MCAF-Net for real-world RSID. The network uses hazy RGB images and dark channel prior (DCP) maps as joint inputs, allowing physical degradation cues to guide end-to-end feature learning. A spatial-frequency residual interaction block introduces a FourierUnit branch into multi-directional spatial interaction to model large-scale haze components. A prior-guided feature attention module adaptively fuses prior and attention features to reduce colour shift and structural distortion. A selective kernel complementary fusion module screens multi-scale skip features through bidirectional residual complementary gating and selective kernel fusion. Extensive experiments demonstrate that DPSF-Net achieves state-of-the-art performance on the real-world RRSHID remote sensing image dehazing benchmark and remains competitive across multiple synthetic datasets. Moreover, the proposed method strikes a favourable balance among restoration quality, parameter count and computational complexity, supporting the effectiveness of dual-prior spatial-frequency modelling.

Abstract

Image Dehazing

Explore similar work

DPSF-Net: A Dual-Prior Spatial-Frequency Network for Real-World Remote Sensing Image Dehazing

RTE-FM-Dehazer: Radiative Transfer Equation Inspired Flow Matching for Real-World Image Dehazing

HNDiff: Haze-Noise Diffusion for Image Dehazing