Fu Xueyang, Liang Borong, Huang Yue, Ding Xinghao, Paisley John
IEEE Trans Neural Netw Learn Syst. 2020 Jun;31(6):1794-1807. doi: 10.1109/TNNLS.2019.2926481. Epub 2019 Jul 22.
Existing deep convolutional neural networks (CNNs) have found major success in image deraining, but at the expense of an enormous number of parameters. This limits their potential applications, e.g., in mobile devices. In this paper, we propose a lightweight pyramid networt (LPNet) for single-image deraining. Instead of designing a complex network structure, we use domain-specific knowledge to simplify the learning process. In particular, we find that by introducing the mature Gaussian-Laplacian image pyramid decomposition technology to the neural network, the learning problem at each pyramid level is greatly simplified and can be handled by a relatively shallow network with few parameters. We adopt recursive and residual network structures to build the proposed LPNet, which has less than 8K parameters while still achieving the state-of-the-art performance on rain removal. We also discuss the potential value of LPNet for other low- and high-level vision tasks.
现有的深度卷积神经网络（CNN）在图像去雨方面取得了重大成功，但代价是参数数量庞大。这限制了它们的潜在应用，例如在移动设备中的应用。在本文中，我们提出了一种用于单图像去雨的轻量级金字塔网络（LPNet）。我们不是设计复杂的网络结构，而是利用特定领域的知识来简化学习过程。具体而言，我们发现通过将成熟的高斯 - 拉普拉斯图像金字塔分解技术引入神经网络，每个金字塔级别的学习问题都得到了极大简化，并且可以由具有较少参数的相对较浅的网络来处理。我们采用递归和残差网络结构来构建所提出的LPNet，该网络参数少于8K，同时在去除雨水方面仍能达到当前的最佳性能。我们还讨论了LPNet在其他低级和高级视觉任务中的潜在价值。
