Efficient Dual-domain Image Dehazing with Haze Prior Perception

2025-07-15

AI Summary

Transformer-based single-image dehazing methods suffer from high computational overhead, insufficient spatial-domain modeling capability under complex haze conditions, and weak coupling between spatial and frequency domains. To address these issues, this paper proposes a dual-domain collaborative dehazing network. Our key contributions are: (1) a dark-channel prior-guided frequency-domain modulation mechanism that dynamically refines prior estimation via closed-loop feedback; (2) a physically consistent spatial-frequency degradation alignment strategy; and (3) a multi-level gated aggregation module coupled with a prior correction guidance branch to enable deep fusion of dual-domain features. Extensive experiments demonstrate state-of-the-art performance on four benchmark datasets, achieving high robustness, real-time inference speed (>30 FPS), and strong generalization capability—particularly for challenging outdoor scenes with heterogeneous haze distributions.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

Transformer-based models exhibit strong global modeling capabilities in single-image dehazing, but their high computational cost limits real-time applicability. Existing methods predominantly rely on spatial-domain features to capture long-range dependencies, which are computationally expensive and often inadequate under complex haze conditions. While some approaches introduce frequency-domain cues, the weak coupling between spatial and frequency branches limits the overall performance. To overcome these limitations, we propose the Dark Channel Guided Frequency-aware Dehazing Network (DGFDNet), a novel dual-domain framework that performs physically guided degradation alignment across spatial and frequency domains. At its core, the DGFDBlock comprises two key modules: 1) the Haze-Aware Frequency Modulator (HAFM), which generates a pixel-level haze confidence map from dark channel priors to adaptively enhance haze-relevant frequency components, thereby achieving global degradation-aware spectral modulation; 2) the Multi-level Gating Aggregation Module (MGAM), which fuses multi-scale features through diverse convolutional kernels and hybrid gating mechanisms to recover fine structural details. Additionally, a Prior Correction Guidance Branch (PCGB) incorporates a closed-loop feedback mechanism, enabling iterative refinement of the prior by intermediate dehazed features and significantly improving haze localization accuracy, especially in challenging outdoor scenes. Extensive experiments on four benchmark haze datasets demonstrate that DGFDNet achieves state-of-the-art performance with superior robustness and real-time efficiency. Code is available at: https://github.com/Dilizlr/DGFDNet.

Problem

• High computational cost limits real-time dehazing with Transformer models
• Existing methods fail under complex haze conditions
• Weak coupling between spatial and frequency domains reduces performance

Innovation

• Dual-domain framework with spatial-frequency alignment
• Haze-Aware Frequency Modulator for spectral modulation
• Multi-level Gating Aggregation for detail recovery