论文标题
条件变异图像降低
Conditional Variational Image Deraining
论文作者
论文摘要
图像deraining是一项重要但具有挑战性的图像处理任务。尽管确定性的图像驱动方法是通过令人鼓舞的性能开发的，但学习概率推断和多种预测的灵活表示是不可行的。此外，雨强度在空间位置和跨色道都不同，这使得这项任务更加困难。在本文中，我们提出了一个有条件的变分图像（CVID）网络，以更好地降低性能，利用条件变异自动编码器（CVAE）的独家生成能力为下雨图像提供多样化的预测。为了执行空间自适应der，我们提出了一个空间密度估计（SDE）模块，以估算每个图像的雨密度图。由于雨水密度在不同的颜色通道上有所不同，因此我们还提出了一个方面的通道（CW）方案。关于合成和现实世界数据集的实验表明，所提出的CVID网络的性能要比图像deraining上的以前的确定性方法好得多。广泛的消融研究验证了我们的CVID网络中提出的SDE模块和CW方案的有效性。该代码可在\ url {https://github.com/yingjun-du/vid}中获得。
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 \url{https://github.com/Yingjun-Du/VID}.
