Dually Connected Deraining Net Using Pixel-Wise Attention
Dually Connected Deraining Net Using Pixel-Wise Attention
复制标题
DOI：
10.1109/lsp.2020.2970345
复制
发表时间：
2020-01
影响因子：
3.9
通讯作者：
Weihong Ren;Jiandong Tian;Qiang Wang;Yandong Tang
中科院分区：
文献类型：
--
作者：
Weihong Ren;Jiandong Tian;Qiang Wang;Yandong Tang
目前的单幅图像去噪方法要么使用递归机制来逐步学习清晰图像和雨图像之间的映射关系，要么侧重于设计各种损失函数来监督学习过程。在这封信中，我们提出了一种基于像素级关注度的双重连通去雨网络，用于单幅图像的降雨。具体地说，去雨网络采用编解码网作为主干，通过联合使用跳跃和连接和跳跃级联连接，可以有效地学习剩余雨纹图。双重连接使去雨网络能够促进各层之间的信息流动，从而使其能够区分和定位雨带。为了保留图像细节，解码后的特征通过可学习的像素级注意力来加权，以自适应地重新校准它们的响应。在人工合成数据集上的实验结果表明，该模型比最新的去重方法具有更好的性能。
Recent single image deraining methods either use a recurrent mechanism to gradually learn the mapping between clear images and rainy images, or focus on designing various loss functions to supervise the learning process. In this letter, we propose a dually connected deraining net using pixel-wise attention, for single image rain removal. Specifically, the deraining net adopts an encoder-decoder net as a backbone, which can effectively learn a residual rain-streaks map by jointly using skip sum connection and skip concatenation connection. The dual connections enable the deraining net to promote information flow between layers, and thus can allow it to discriminate and localize the rain streaks. To preserve image details, the decoded features are weighted by the learnable pixel-wise attention for adaptively recalibrating their responses. Experimental results on synthetic datasets demonstrate that the proposed model outperforms the recent state-of-the-art deraining methods.