HistoFusionNet: Histogram-Guided Fusion and Frequency-Adaptive Refinement for Nighttime Image Dehazing

Mohammad Heydari; Wei Dong; Shahram Shirani; Jun Chen; Han Zhou

cs.CVApr 4, 2026

HistoFusionNet: Histogram-Guided Fusion and Frequency-Adaptive Refinement for Nighttime Image Dehazing

Authors: Mohammad Heydari, Wei Dong, Shahram Shirani, Jun Chen, Han Zhou

Organizations: McMaster University

Abstract

Nighttime image dehazing remains a challenging low-level vision problem due to the joint presence of haze, glow, non-uniform illumination, color distortion, and sensor noise, which often invalidate assumptions commonly used in daytime dehazing. To address these challenges, we propose HistoFusionNet, a transformer-enhanced architecture tailored for nighttime image dehazing by combining histogram-guided representation learning with frequency-adaptive feature refinement. Built upon a multi-scale encoder-decoder backbone, our method introduces histogram transformer blocks that model long-range dependencies by grouping features according to their dynamic-range characteristics, enabling more effective aggregation of similarly degraded regions under complex nighttime lighting. To further improve restoration fidelity, we incorporate a frequency-aware refinement branch that adaptively exploits complementary low- and high-frequency cues, helping recover scene structures, suppress artifacts, and enhance local details. This design yields a unified framework that is particularly well suited to the heterogeneous degradations encountered in real nighttime hazy scenes. Extensive experiments and highly competitive performance of our method on the NTIRE 2026 Nighttime Image Dehazing Challenge benchmark demonstrate the effectiveness of the proposed method. Our team ranked 1st among 22 participating teams, highlighting the robustness and competitive performance of HistoFusionNet. The code is available at: https://github.com/heydarimo/Night-Time-Dehazing

Figures & tables

Figure 2: Overall architecture of HistoFusionNet . Our dehazing network adopts a U-shaped design with a DCNv4-based main branch and an auxiliary frequency-aware branch. Histogram transformer blocks are inserted at the bottleneck to perform dynamic-range aware global aggregation, while a lightweight frequency-adaptive refinement module is employed to enhance color fidelity and recover fine details.

Methods	NH-HAZE [ 3 ]		NH-HAZE2 [ 1 ]		Dense-Haze [ 2 ]		Challenge-Data
Methods	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$
SFSNiD (CVPR 2024) [ 13 ]	17.318	0.523	18.017	0.720	15.201	0.392	—	—
SFMN (TIP 2025) [ 43 ]	20.366	0.687	18.878	0.776	16.855	0.587	—	—
DWT-FFC (CVPR 2023) [ 60 ]	21.621	0.706	21.383	0.846	17.103	0.588	—	—
DehazeDCT (CVPR 2024) [ 23 ]	21.632	0.702	22.345	0.846	17.861	0.592	27.465	0.899
HistoFusionNet (Ours)	21.972	0.710	22.415	0.847	18.314	0.611	27.879	0.905

Table 1: Quantitative comparisons between our proposed HistoFusionNet and SOTA methods. Our proposed method achieves superior performance in terms of PSNR and SSIM across four datasets. These numbers are obtained from training with their released code. [Key: Best , Second Best ,

\uparrow

(

\downarrow

): Larger (smaller) values leads to better performance, Challenge-Data: Official dataset for NTIRE 2026 Nighttime Image Dehazing Challenge]

Figure 3: Visual comparisons on NH-HAZE dataset. Compared to other models, our method exhibits higher color fidelity and effective dehazing, yielding compelling results.

Figure 4: Visual experiment results on NH-HAZE2 dataset. Obviously, our method demonstrates superior performance on color preservation and detail maintaining, further enhancing the overall quality of the output.

Figure 5: Qualitative comparison on the Dense-Haze dataset. Our method produces clearer structures, better color fidelity, and more faithful detail recovery, leading to higher overall visual quality.

Team	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	MUSIQ $\uparrow$	NIQE $\downarrow$	FID $\downarrow$	Final Rank $\downarrow$
HistoDeHaze	27.88	0.91	0.10	60.40	3.77	72.25	1
XJRes	27.44	0.91	0.11	63.26	3.99	64.73	2
KETI	27.30	0.90	0.11	64.05	3.68	74.47	3
crivoic	26.84	0.90	0.11	64.54	3.64	90.65	4
mi_camera	26.83	0.89	0.12	65.25	3.95	86.06	5

Table 2: Final ranking (top 5 teams) of the NTIRE 2026 Nighttime Dehazing Challenge. Red and blue indicate the best and second-best results, respectively. Final Rank is reported directly from the official results. [Key: Best , Second Best ,

\uparrow(\downarrow)

: larger (smaller) is better.]

Figure 6: Our results on the validation set of the NTIRE 2026 Nighttime Image Dehazing Challenge, demonstrating strong dehazing performance with improved visibility, clearer structures, and more faithful color restoration.

Configurations	PSNR $\uparrow$	SSIM $\uparrow$
w/o frequency-adaptive refinement	18.103	0.600
w/o histogram transformer blocks	17.861	0.592
w/o frequency-aware branch	17.984	0.597

Table 3: The ablation result of our method on the Dense-Haze dataset. Each component of our HistoFusionNet contribute positively to our final dehazing performance.

Image Dehazing

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

See all 35 papers

CLIP-Guided Data Augmentation for Night-Time Image Dehazing
Apr 7, 2026Xining Ge, Weijun Yuan, Gengjia Chang +2Image Dehazing Data Augmentation
Hangzhou Dianzi University · Jinan University · Hefei University of Technology +2
Transmittance-Guided Structure-Texture Decomposition for Nighttime Image Dehazing
Mar 31, 2026Francesco Moretti, Giulia Bianchi, Andrea GalloImage Dehazing Physics-Guided Image Restoration
Maharaja Agrasen University
DDR-Net: Haze-Aware Dual-Domain Refinement for Single-Image Dehazing
Jul 13, 2026Xinye Zheng, Ye Yu, Qiang Lu +3Image Restoration Image Dehazing
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China

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

CLIP-Guided Data Augmentation for Night-Time Image Dehazing

Xining Ge, Weijun Yuan, Gengjia Chang, Xuyang Li+1

Hangzhou Dianzi University · Jinan University · Hefei University of Technology+2

Image Dehazing Data Augmentation

Open paper AskPDF arXiv

Nighttime image dehazing faces a more complex degradation pattern than its daytime counterpart, as haze scattering couples with low illumination, non-uniform lighting, and strong light interference. Under limited supervision, this complexity aggravates domain drift and training instability, since target-domain samples are scarce while naively introducing external data may weaken adaptation due to distribution mismatch. This paper presents our solution to the NTIRE 2026 Night Time Image Dehazing Challenge, built as a unified framework that integrates domain-aligned data construction, stage-wise training, and inference-time enhancement. Specifically, a pre-trained CLIP visual encoder screens candidate external samples by similarity to construct training data closer to the target domain. NAFNet is then trained in two stages, first adapting to the target domain and then expanding to broader degradation patterns. At inference time, TLC, x8 self-ensemble, and weighted snapshot fusion are combined to improve output stability. Rather than relying on complex network redesign, the proposed framework offers a practical and effective pipeline for nighttime image dehazing.

Abstract

Image Dehazing

Explore similar work

CLIP-Guided Data Augmentation for Night-Time Image Dehazing

Transmittance-Guided Structure-Texture Decomposition for Nighttime Image Dehazing

DDR-Net: Haze-Aware Dual-Domain Refinement for Single-Image Dehazing