arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.09677cs.CVcs.AIcs.MM
收藏

单幅图像的渐变网络去噪

Gradual Network for Single Image De-raining

University of Wisconsin-Madison(威斯康星大学麦迪逊分校);Sun Yat-sen University(中山大学);SenseTime Research(商汤科技研究院)

Zhe Huang, Weijiang Yu, Wayne Zhang, Litong Feng, Nong Xiao

摘要:

单幅图像去雨的最大进展遇到了一个关键的挑战,即去除不同尺度和形状的雨条纹,同时保持图像的细节。现有的单图像去雨方法将雨纹去除直接视为逐像素回归的过程。然而,他们缺乏挖掘过度去雨(例如,在无雨区域去除纹理细节)和欠去雨(例如,留下雨条纹)之间的平衡。在本文中,我们首先提出了一个由粗到细的网络称为渐进网络(GraNet),由粗阶段和细阶段,用于研究不同粒度的单张图像去雨。具体来说,为了揭示粗粒度的雨纹特征(例如长而厚的雨纹/雨滴),我们提出了一个粗糙的阶段,通过利用局部-全局空间依赖性通过局部-全局子网络组成的区域感知块。取残差结果(粗糙的去雨结果)之间的雨图像样本(即输入数据)和粗调级的输出(即,学习的雨掩模)作为输入,细雨阶段通过去除细粒雨条纹来继续除雨(例如,小雨条纹和水雾),以通过统一的上下文合并子系统获得无雨和良好重建的输出图像。网络中有密集块和合并块。对合成数据和真实数据进行的扎实而全面的实验表明,我们的GraNet可以通过去除各种密度,尺度和形状的雨条纹,同时保持无雨区域的图像细节,从而显着优于最先进的方法。

英文摘要:

Most advances in single image de-raining meet a key challenge, which is removing rain streaks with different scales and shapes while preserving image details. Existing single image de-raining approaches treat rain-streak removal as a process of pixel-wise regression directly. However, they are lacking in mining the balance between over-de-raining (e.g. removing texture details in rain-free regions) and under-de-raining (e.g. leaving rain streaks). In this paper, we firstly propose a coarse-to-fine network called Gradual Network (GraNet) consisting of coarse stage and fine stage for delving into single image de-raining with different granularities. Specifically, to reveal coarse-grained rain-streak characteristics (e.g. long and thick rain streaks/raindrops), we propose a coarse stage by utilizing local-global spatial dependencies via a local-global subnetwork composed of region-aware blocks. Taking the residual result (the coarse de-rained result) between the rainy image sample (i.e. the input data) and the output of coarse stage (i.e. the learnt rain mask) as input, the fine stage continues to de-rain by removing the fine-grained rain streaks (e.g. light rain streaks and water mist) to get a rain-free and well-reconstructed output image via a unified contextual merging sub-network with dense blocks and a merging block. Solid and comprehensive experiments on synthetic and real data demonstrate that our GraNet can significantly outperform the state-of-the-art methods by removing rain streaks with various densities, scales and shapes while keeping the image details of rain-free regions well-preserved.

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。

↑