Figure 2. The architecture of the proposed SPANet (a). It adopts three standard residual blocks (RB)  to extract features, four spatial attentive blocks (SAB) to identify rain streaks progressively in four stages, and two residual blocks to reconstruct a clean background. A SAB (b) contains three spatial attentive residual blocks (SARB) (c) and one spatial attentive module (SAM) (d). Dilation convolutions  are used in RB and SARB.
Figure 3. Visual comparison of the state-of-the-art CNN-based derainers and the proposed SPANet on some real rain images collected from previous derain papers and the Internet. Note that the state-of-the-art CNN-based derainers are trained on their original dataset.
|Methods||Rain Images||DSC |
Table 1. Quantitative results of the benchmarked state-of-the-art derainers as well as the proposed SPANet on the proposed test set. The original codes of all these derainers are used for evaluation. We also train CNN based state-of-the-art methods [11, 40, 42, 25] on our dataset, and results are in brackets. Best performance is marked in bold. Note that due to lack of density label of rain streaks in our dataset, we only ﬁne-tune the pre-trained model of DID-MDN  without training label classiﬁcation network.
Code : Github
* The training dataset contains 660K+ patches croped from 28.5K rain images.
* Due to the copyright of some videos from the Internet, we cannot public the original videos.