发表机构
School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对单图像去雾，提出DDR-Net，基于雾先验提取器、细节增强块、空间 - 频率瓶颈细化三个模块，有效解决现有方法瓶颈阶段特征细化不足等问题，在真实世界和合成数据集上实验效果良好，优于现有去雾方法。
AI 中文摘要
单图像去雾旨在从雾退化图像中恢复清晰场景。由于大气散射和现实世界雾分布的复杂性，这仍然具有挑战性。尽管最近的端到端网络取得了有前景的性能，但两个问题限制了其有效性：瓶颈阶段特征细化不足和编码器 - 解码器架构中局部结构表示薄弱。因此，提出了用于单图像去雾的雾感知双域细化网络（DDR-Net）。该方法基于三个模块构建：雾先验提取器（HPE）通过直接对下采样的模糊图像操作提供多尺度雾感知先验；细节增强块（DE块）作为核心特征提取单元，捕获多尺度结构信息并通过梯度感知卷积增强边缘和纹理恢复；瓶颈处的空间 - 频率瓶颈细化（SFBR）联合利用空间和频率信息细化瓶颈特征。DDR-Net实现了更有效的特征表示和雾去除重建。在真实世界基准上的大量实验表明，该方法优于现有去雾方法，在合成数据集上也具有竞争力。
英文摘要
Single-image dehazing aims to recover clear scenes from haze-degraded images. It remains challenging due to the atmospheric scattering and the complexity of real-world haze distributions. Although recent end-to-end networks have achieved promising performance, two issues still limit their effectiveness: insufficient feature refinement at the bottleneck stage and weak local structural representation in encoder-decoder architectures. Thus, we propose a Haze-Aware Dual-Domain Refinement Network (DDR-Net) for single-image dehazing. Our method is built upon three modules: Haze Prior Extractor (HPE) provides multi-scale haze-aware priors by operating directly on downsampled hazy images; Detail-Enhanced Blocks (DE Blocks) serve as the core feature extraction units, capturing multi-scale structural information and enhancing edge and texture recovery via gradient-aware convolutions; and Spatial-Frequency Bottleneck Refinement (SFBR) at the bottleneck jointly exploits spatial and frequency information to refine bottleneck features. DDR-Net achieves more effective feature representation and reconstruction for haze removal. Extensive experiments on real-world benchmarks demonstrate that our method outperforms existing dehazing approaches. It achieves competitive performance on synthetic datasets.
CommentsAccepted by PRCV 2026
