Computer Vision and Image Understanding ( IF 4.5 ) Pub Date : 2020-09-14 , DOI: 10.1016/j.cviu.2020.103106 Nanfeng Jiang , Weiling Chen , Liqun Lin , Tiesong Zhao
Rain streaks severely degenerate the performances of image/video processing tasks, therefore effective methods for removing rain streaks are required for a wide range of practical applications. In this paper, we introduce an end-to-end deep network, called GridDerainNet, to remove rain streaks within single image under different conditions. The architecture of GridDerainNet consists of three modules: pre-processing, multi-scale attentive module and post-processing. The pre-processing module can effectively generate several variants of the given rainy image, in order to extract more key features from the input. The multi-scale attentive module implements a novel attention mechanism, which allows more flexible information exchange and aggregation, taking full use of diversities of a given image. In the end, post-processing module furthers to reduce residual artifacts after previous two steps. Quantitative and qualitative experimental results demonstrate that the proposed algorithm outperforms several state-of-the-art methods on both synthetic and real-world images.
中文翻译:
通过多模块深网格网络去除单个图像的雨水
雨纹严重降低了图像/视频处理任务的性能,因此,广泛的实际应用需要有效的方法来去除雨纹。在本文中,我们引入了一个名为GridDerainNet的端到端深度网络,以消除不同条件下单个图像中的雨水条纹。GridDerainNet的体系结构包含三个模块:预处理,多尺度关注模块和后处理。预处理模块可以有效地生成给定雨季图像的多个变体,以便从输入中提取更多关键特征。多尺度注意模块实现了一种新颖的注意机制,该机制可以充分利用给定图像的多样性来实现更灵活的信息交换和聚合。到底,后处理模块进一步减少了前两个步骤后的残留伪像。定量和定性的实验结果表明,该算法在合成图像和真实图像上均优于几种最新技术。