Efficient Dual-domain Image Dehazing with Haze Prior Perception

TL;DR

This paper introduces DGFDNet, a dual-domain image dehazing network that explicitly aligns spatial and frequency information using haze priors, achieving state-of-the-art results with improved robustness and efficiency.

Contribution

The paper proposes a novel dual-domain framework with haze-aware frequency modulation and multi-scale feature fusion, explicitly aligning spatial and frequency domains for superior dehazing performance.

Findings

Achieves state-of-the-art dehazing results on benchmark datasets.

Demonstrates improved robustness and real-time efficiency.

Effectively utilizes dark channel priors for adaptive spectral filtering.

Abstract

Transformers offer strong global modeling for single-image dehazing but come with high computational costs. Most methods rely on spatial features to capture long-range dependencies, making them less effective under complex haze conditions. Although some integrate frequency-domain cues, weak coupling between spatial and frequency branches limits their performance. To address these issues, we propose the Dark Channel Guided Frequency-aware Dehazing Network (DGFDNet), a dual-domain framework that explicitly aligns degradation across spatial and frequency domains. At its core, the DGFDBlock consists of two key modules: 1) Haze-Aware Frequency Modulator (HAFM), which uses dark channel priors to generate a haze confidence map for adaptive frequency modulation, achieving global degradation-aware spectral filtering. 2) Multi-level Gating Aggregation Module (MGAM), which fuses multi-scale features via multi-scale convolutions and a hybrid gating mechanism to recover fine-grained structures. Additionally, the Prior Correction Guidance Branch (PCGB) incorporates feedback for iterative refinement of the prior, improving haze localization accuracy, particularly in outdoor scenes. Extensive experiments on four benchmark datasets demonstrate that DGFDNet achieves state-of-the-art performance with improved robustness and real-time efficiency. Code is available at: https://github.com/Dilizlr/DGFDNet.