HazeSpikeMamba: Coupling Spiking-Inspired and State-Space Features for Self-Supervised Real-World Dehazing

📄 arXiv: 2608.06886v1 📥 PDF

作者: Haoran Liu, Huibin Li, Mingzhe Liu, Peng Li, Guibin Zan

分类: cs.CV

发布日期: 2026-08-07

备注: 21 pages, 6 figures

💡 一句话要点

提出HazeSpikeMamba以解决真实场景去雾问题

🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture) 支柱八：物理动画 (Physics-based Animation)

关键词: 去雾技术 脉冲神经网络 状态空间模型 自监督学习 图像处理

📋 核心要点

  1. 现有去雾方法在真实场景中的表现不佳，主要由于合成雾霾无法充分反映真实世界的复杂性。
  2. HazeSpikeMamba通过结合局部脉冲神经网络和全局注意力机制，提出了一种新的去雾框架，增强了模型的适应性。
  3. 实验结果表明，HazeSpikeMamba在多个数据集上显著提升了BRISQUE和NIMA指标，验证了其有效性。

📝 摘要（中文）

去雾网络通常在合成的雾霾-清晰图像对上训练，但在真实照片上的表现往往下降。合成雾霾无法完全捕捉真实雾霾的变异性，而配对的真实雾霾-清晰图像稀缺。本文提出HazeSpikeMamba，一个紧凑的去雾框架，结合了受脉冲神经网络启发的局部路径和注意力状态空间全局路径，采用多尺度U-Net结构。局部路径使用新的脉冲发射方案TPCNNSpike，能够并行更新神经元状态。全局路径则适应了MambaIRv2的注意力状态空间模块，保留语义提示和序列重排序，同时去除了窗口自注意力分支。通过冻结的退化网络进行目标域适应，重建误差仅更新HazeSpikeMamba的最终恢复层，且无需无雾标签。

🔬 方法详解

问题定义：本文旨在解决现有去雾网络在真实场景中表现不佳的问题，主要由于合成雾霾无法全面捕捉真实雾霾的多样性，以及缺乏配对的真实雾霾-清晰图像。

核心思路：HazeSpikeMamba的核心思路是结合受脉冲神经网络启发的局部路径和全局注意力状态空间路径，以增强模型在真实场景中的适应性和去雾效果。通过这种设计，模型能够更好地处理复杂的雾霾情况。

技术框架：HazeSpikeMamba采用多尺度U-Net结构，包含局部路径和全局路径。局部路径使用TPCNNSpike进行并行神经元更新，而全局路径则利用MambaIRv2的注意力状态空间模块来建模长距离依赖关系。

关键创新：最重要的创新在于引入了TPCNNSpike脉冲发射机制和适应性状态空间模块，这使得模型在处理复杂场景时表现出更高的灵活性和准确性。

关键设计：HazeSpikeMamba的前向网络包含2.02M个活跃参数，要求13.27G的名义MACs。通过冻结的退化网络进行目标域适应，重建误差仅更新最终恢复层，且适应过程不依赖于无雾标签。

🖼️ 关键图片

img_0
img_1
img_2

📊 实验亮点

在RTTS数据集上，HazeSpikeMamba的BRISQUE指标从30.13降低至27.72，NIMA指标从4.13提升至4.87，显示出显著的性能提升。此外，该模型在URHI和HSTS数据集上也取得了最佳的BRISQUE和NIMA表现，验证了其优越性。

🎯 应用场景

该研究的潜在应用领域包括无人驾驶、监控视频处理和环境监测等。通过有效去雾，HazeSpikeMamba能够提升图像质量，增强视觉系统在复杂环境中的表现，具有重要的实际价值和广泛的应用前景。

📄 摘要（原文）

Dehazing networks are commonly trained on synthetic hazy-clear pairs, but their performance often drops on real photographs. Synthetic haze generated using the atmospheric scattering model does not fully capture the variability of real haze, and paired real hazy-clear images are scarce. In this work, we propose HazeSpikeMamba, a compact dehazing framework that combines a spiking-inspired local path and an attentive state-space global path in a multi-scale U-Net. The local path uses TPCNNSpike, a new spike-emission scheme inspired by the neighborhood coupling of Pulse-Coupled Neural Network (PCNN). Unlike grouped directional scanning, TPCNNSpike updates all neurons in parallel using the previous firing states of their Gaussian-weighted neighborhoods. The global path adapts the Attentive State-Space Module of MambaIRv2, retaining semantic prompting and sequence reordering while removing the window self-attention branch. Its state-space processing models long-range dependencies with complexity linear in sequence length. For target-domain adaptation, a frozen degradation network, pretrained on paired NH-HAZE data, re-synthesizes haze from the dehazed prediction. The reconstruction error updates only the final restoration layers of HazeSpikeMamba without haze-free labels during adaptation. A shared checkpoint is adapted once on each complete unlabeled target set, making the evaluation dataset-level and transductive rather than zero-shot or per-image optimization. The forward network contains 2.02M active parameters and requires 13.27G nominal MACs (measured with thop at 256x256 input). This adaptation consistently improves BRISQUE and NIMA on RTTS, URHI, and HSTS. On RTTS, BRISQUE decreases from 30.13 to 27.72 and NIMA increases from 4.13 to 4.87. Under this transductive protocol, the adapted model also achieves the best BRISQUE and NIMA on URHI and HSTS among the compared methods.