Density-aware Single Image De-raining using a Multi-stream Dense Network
About
Single image rain streak removal is an extremely challenging problem due to the presence of non-uniform rain densities in images. We present a novel density-aware multi-stream densely connected convolutional neural network-based algorithm, called DID-MDN, for joint rain density estimation and de-raining. The proposed method enables the network itself to automatically determine the rain-density information and then efficiently remove the corresponding rain-streaks guided by the estimated rain-density label. To better characterize rain-streaks with different scales and shapes, a multi-stream densely connected de-raining network is proposed which efficiently leverages features from different scales. Furthermore, a new dataset containing images with rain-density labels is created and used to train the proposed density-aware network. Extensive experiments on synthetic and real datasets demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art methods. In addition, an ablation study is performed to demonstrate the improvements obtained by different modules in the proposed method. Code can be found at: https://github.com/hezhangsprinter
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Image Deraining | Rain100L (test) | PSNR25.23 | 161 | |
| Image Deraining | Rain100L | PSNR25.23 | 152 | |
| Deraining | Rain100L (test) | PSNR23.79 | 90 | |
| Image Deraining | Test100 (test) | PSNR22.56 | 53 | |
| Image Deraining | Rain100H | PSNR17.35 | 52 | |
| Deraining | Rain100H (test) | PSNR17.35 | 50 | |
| Image Deraining | Rain100H (test) | PSNR17.35 | 40 | |
| Image Deraining | 2800 (test) | PSNR28.13 | 34 | |
| Image Deraining | 1200 (test) | PSNR29.65 | 28 | |
| Image Deraining | Average across Deraining Datasets (test) | PSNR24.58 | 26 |