基于一致性伪标签生成与协同展开网络的真实场景图像去雾
Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network
AI总结：
针对真实场景图像去雾（RID）中真实雾气分布建模复杂和配对数据稀缺的问题，提出协同展开网络融合物理知识恢复细节，并构建首个基于一致性的标签生成器生成伪标签，实现RID任务的最先进性能。
摘要：
真实场景图像去雾（RID）旨在缓解真实场景中雾气导致的图像退化。由于准确建模真实雾气分布的复杂性以及真实场景配对数据的稀缺性，该任务仍具挑战性。为此，我们首先引入协同展开网络，联合建模大气散射与图像场景，将物理知识有效融入深度网络以恢复受雾污染的细节。此外，我们提出首个面向RID的迭代均值教师框架，即基于一致性的标签生成器，为网络训练生成高质量伪标签。具体而言，我们提供最优标签池存储训练中最佳伪标签，利用全局与局部一致性选择优质候选并分配权重以优先处理无雾区域。实验验证了方法的有效性，其在RID任务上达到最先进性能。代码将发布于https://github.com/cnyvfang/CORUN-Colabator。
英文摘要：
Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real haze distributions and the scarcity of paired real-world data. To address these challenges, we first introduce a cooperative unfolding network that jointly models atmospheric scattering and image scenes, effectively integrating physical knowledge into deep networks to restore haze-contaminated details. Additionally, we propose the first RID-oriented iterative mean-teacher framework, termed the Coherence-based Label Generator, to generate high-quality pseudo labels for network training. Specifically, we provide an optimal label pool to store the best pseudo-labels during network training, leveraging both global and local coherence to select high-quality candidates and assign weights to prioritize haze-free regions. We verify the effectiveness of our method, with experiments demonstrating that it achieves state-of-the-art performance on RID tasks. Code will be available at https://github.com/cnyvfang/CORUN-Colabator.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
