Image deraining is an important yet challenging image processing task. Though deterministic image deraining methods are developed with encouraging performance, they are infeasible to learn flexible representations for probabilistic inference and diverse predictions. Besides, rain intensity varies both in spatial locations and across color channels, making this task more difficult. In this paper, we propose a Conditional Variational Image Deraining (CVID) network for better deraining performance, leveraging the exclusive generative ability of Conditional Variational Auto-Encoder (CVAE) on providing diverse predictions for the rainy image. To perform spatially adaptive deraining, we propose a spatial density estimation (SDE) module to estimate a rain density map for each image. Since rain density varies across different color channels, we also propose a channel-wise (CW) deraining scheme. Experiments on synthesized and real-world datasets show that the proposed CVID network achieves much better performance than previous deterministic methods on image deraining. Extensive ablation studies validate the effectiveness of the proposed SDE module and CW scheme in our CVID network. The code is available at https://github.com/Yingjun-Du/VID.

中文翻译：

---

条件变分图像消除。

图像排空是一项重要但具有挑战性的图像处理任务。尽管确定性的图像消除方法开发出令人鼓舞的性能，但它们难以学习用于概率推断和各种预测的灵活表示。此外，降雨强度在空间位置和整个色彩通道中都不同，这使这项任务更加困难。在本文中，我们利用条件变分自动编码器（CVAE）的独有生成能力，为雨天图像提供多种预测，提出了一种条件变分图像排水（CVID）网络，以实现更好的排水性能。为了执行空间自适应排水，我们提出了一个空间密度估计（SDE）模块来估计每个图像的降雨密度图。由于不同颜色通道的降雨密度不同，我们还提出了一种基于信道的（CW）清除方案。在合成和真实数据集上进行的实验表明，所提出的CVID网络比以前的确定性方法在图像排水方面具有更好的性能。广泛的消融研究证实了我们的CVID网络中提出的SDE模块和CW方案的有效性。该代码位于https://github.com/Yingjun-Du/VID。