使用非对称循环生成对抗框架的深度单图像去雨
Deep Single Image Deraining using An Asymetric Cycle Generative and Adversarial Framework
AI总结：
针对雨雾共存场景下无监督去雨方法性能差、样本缺乏多样性的问题，提出非对称循环生成对抗框架ACGF，通过R2C和C2R转换块及ARFE、RFDR网络同时提取雨雾特征并提升合成图像纹理细节，在基准数据集上优于现有方法。
摘要：
现实中，雨和雾通常同时存在，这会大大降低场景图像的清晰度和质量。然而，大多数无监督单图像去雨方法主要通过忽略雾来去除雨纹，导致去雨性能低下。此外，这些方法生成的样本相当同质且缺乏多样性，在面对复杂雨天场景时效果不佳。为了解决上述问题，我们提出了一种新颖的非对称循环生成对抗框架（ACGF）用于单图像去雨，该框架在合成和真实雨天图像上进行训练，同时捕获雨纹和雾特征。ACGF由雨雾到清洁（R2C）转换块和清洁到雨雾（C2R）转换块组成。前者由雨和去雨雾网络以及注意力雨雾特征提取网络（ARFE）构成的并行去雨路径和雨雾特征提取路径组成，而后者仅包含合成雨转换路径。在雨雾特征提取路径中，为了更好地表征雨雾融合特征，我们采用ARFE通过学习空间特征相关性来利用全局和局部雨雾信息的自相似性。此外，为了提高C2R的转换能力和模型的多样性，我们通过嵌入雨天图像退化模型和混合判别器设计了雨雾特征解耦重组网络（RFDR），以在合成雨转换路径中保留更丰富的纹理细节。在基准雨雾和雨数据集上的大量实验表明，ACGF优于最先进的去雨方法。我们还进行了去雾性能评估实验，进一步证明了ACGF的有效性。
英文摘要：
In reality, rain and fog are often present at the same time, which can greatly reduce the clarity and quality of the scene image. However, most unsupervised single image deraining methods mainly focus on rain streak removal by disregarding the fog, which leads to low-quality deraining performance. In addition, the samples are rather homogeneous generated by these methods and lack diversity, resulting in poor results in the face of complex rain scenes. To address the above issues, we propose a novel Asymetric Cycle Generative and Adversarial framework (ACGF) for single image deraining that trains on both synthetic and real rainy images while simultaneously capturing both rain streaks and fog features. ACGF consists of a Rain-fog2Clean (R2C) transformation block and a Clean2Rain-fog (C2R) transformation block. The former consists of parallel rain removal path and rain-fog feature extraction path by the rain and derain-fog network and the attention rain-fog feature extraction network (ARFE) , while the latter only contains a synthetic rain transformation path. In rain-fog feature extraction path, to better characterize the rain-fog fusion feature, we employ an ARFE to exploit the self-similarity of global and local rain-fog information by learning the spatial feature correlations. Moreover, to improve the translational capacity of C2R and the diversity of models, we design a rain-fog feature decoupling and reorganization network (RFDR) by embedding a rainy image degradation model and a mixed discriminator to preserve richer texture details in synthetic rain conversion path. Extensive experiments on benchmark rain-fog and rain datasets show that ACGF outperforms state-of-the-art deraining methods. We also conduct defogging performance evaluation experiments to further demonstrate the effectiveness of ACGF.
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。
