DRD-Net: Detail-recovery Image Deraining via Context Aggregation Networks
DRD-Net: Detail-recovery Image Deraining via Context Aggregation Networks
复制标题
DOI：
--
复制
发表时间：
2019-08
期刊：
影响因子：
--
通讯作者：
Sen Deng;Mingqiang Wei;Jun Wang;Luming Liang;Haoran Xie;Meng Wang
中科院分区：
文献类型：
--
作者：
Sen Deng;Mingqiang Wei;Jun Wang;Luming Liang;Haoran Xie;Meng Wang
图像去伪是计算机视觉和图形学中的一个基本问题，至今尚未得到很好的解决。传统的图像去噪方法在去除中、大雨时往往效果不佳，而基于学习的去噪方法则会导致图像细节丢失、光晕伪影和/或颜色失真等图像质量下降。与现有的图像deraining方法，缺乏细节恢复机制，我们提出了一个端到端的细节恢复图像deraining网络（称为DRD-Net）的单一图像。我们首次引入了两个具有综合损失函数的子网络，它们协同作用，以消除和恢复因去盲而丢失的细节。我们有三个关键贡献。首先，我们提出了一个雨残差网络，以消除雨条纹从下雨的图像，它结合了挤压和激励（SE）操作与残差块，充分利用空间上下文信息。其次，我们设计了一个新的连接风格块，命名为结构细节上下文聚合块（SDCAB），它聚合上下文特征信息，并具有一个大的接收字段。第三，借鉴SDCAB，我们构建了一个细节修复网络，鼓励丢失的细节返回，消除图像退化。我们已经在四个公认的数据集（三个合成数据集和一个真实世界数据集）上验证了我们的方法。定量和定性的比较表明，我们的方法优于国家的最先进的去水印方法在去水印的鲁棒性和细节的准确性。源代码已在GitHub上供公众评估和使用。
Image deraining is a fundamental, yet not well-solved problem in computer vision and graphics. The traditional image deraining approaches commonly behave ineffectively in medium and heavy rain removal, while the learning-based ones lead to image degradations such as the loss of image details, halo artifacts and/or color distortion. Unlike existing image deraining approaches that lack the detail-recovery mechanism, we propose an end-to-end detail-recovery image deraining network (termed a DRD-Net) for single images. We for the first time introduce two sub-networks with a comprehensive loss function which synergize to derain and recover the lost details caused by deraining. We have three key contributions. First, we present a rain residual network to remove rain streaks from the rainy images, which combines the squeeze-and-excitation (SE) operation with residual blocks to make full advantage of spatial contextual information. Second, we design a new connection style block, named structure detail context aggregation block (SDCAB), which aggregates context feature information and has a large reception field. Third, benefiting from the SDCAB, we construct a detail repair network to encourage the lost details to return for eliminating image degradations. We have validated our approach on four recognized datasets (three synthetic and one real-world). Both quantitative and qualitative comparisons show that our approach outperforms the state-of-the-art deraining methods in terms of the deraining robustness and detail accuracy. The source code has been available for public evaluation and use on GitHub.