HNDiff：用于图像去雾的雾霾-噪声扩散模型
HNDiff: Haze-Noise Diffusion for Image Dehazing
浏览论文内容
中文总结 AI 辅助
本文提出嵌入大气散射模型的HNDiff扩散框架，通过雾霾感知噪声调度器关联正向退化物理机制，反向同步去雾去噪，改进主流去雾骨干网络并在基准数据集达最优结果。
中文摘要 AI 辅助
现有基于扩散的方法近期在图像去雾领域取得了显著进展，但这类方法通常忽略雾霾形成的物理机制，且从纯高斯噪声中重建清晰图像，从而限制了其复原潜力。为解决该问题，本文提出Haze-Noise Diffusion（HNDiff，雾霾-噪声扩散），一种将大气散射模型作为归纳偏置嵌入的新型扩散框架。通过将扩散过程建立在物理原理之上，HNDiff确保复原结果更贴合雾霾形成的底层机制。在正向过程中，本文引入带有雾霾感知噪声调度器的联合雾霾-噪声扩散，逐步向图像中添加雾霾与噪声；本质上，该调度器会根据雾霾密度调整噪声水平：雾霾较浓的区域注入更强噪声以促进内容生成，而更清晰的区域注入更弱噪声以更好保留细节，这直接将正向退化过程与雾霾物理机制关联起来。在反向过程中，本文推导了物理一致的去雾-去噪过程，该过程同时去除雾霾与噪声，以贴合正向退化过程的方式复原清晰图像。为进一步提升实用性，本文提出Latent HNDiff，其编译的潜在清晰先验可无缝集成到现有去雾网络中以提升性能。大量实验表明，本文工作显著改进了主流去雾骨干网络，并在基准数据集上达到了最优结果。项目页面可访问此https URL。
英文摘要
Existing diffusion-based methods have recently made significant progress in image dehazing. However, they typically neglect the physics of haze formation and reconstruct clean images from pure Gaussian noise, thereby limiting their restoration potential. To address this issue, we propose Haze-Noise Diffusion (HNDiff), a novel diffusion framework that embeds the atmospheric scattering model as an inductive bias. By grounding diffusion in physical principles, HNDiff ensures that the restoration aligns more closely with underlying mechanisms of haze formation. In its forward process, we introduce joint haze-noise diffusion with a haze-aware noise scheduler, which progressively adds both haze and noise to an image. Essentially, the scheduler adapts noise levels according to haze density, meaning that regions with heavier haze receive stronger noise injection to encourage content generation, while clearer regions receive lighter noise to better preserve details, which directly links the forward degradation process with the physics of haze. In the reverse process, we then derive a physically consistent dehazing-denoising process that simultaneously removes haze and noise to restore a clean image in a manner aligned with the forward degradation process. To further enhance practicality, we propose Latent HNDiff, which compiles clean latent priors that can be seamlessly integrated into existing dehazing networks to boost performance. Extensive experiments show that our work significantly improves leading dehazing backbones and achieves state-of-the-art results on benchmark datasets. The project page is available at https://jin-ting-he.github.io/HNDiff .
发表机构
- National Yang Ming Chiao Tung University（国立阳明交通大学）
- National Tsing Hua University（国立清华大学）
- National Chengchi University（国立政治大学）
- NVIDIA（英伟达）
机构由 AI 辅助整理，请以论文原文为准。
