Name
Abstract | ||
|---|---|---|
Single image deraining task is still a very challenging task due to its ill-posed nature in reality. Recently, researchers have tried to fix this issue by training the CNN-based end-to-end models, but they still cannot extract the negative rain streaks from rainy images precisely, which usually leads to an over de-rained or under de-rained result. To handle this issue, this paper proposes a new coarse-to-fine single image deraining framework termed Multi-stream Hybrid Deraining Network (shortly, MH-DerainNet). To obtain the negative rain streaks during training process more accurately, we present a new module named dual path residual dense block, i.e., Residual path and Dense path. The Residual path is used to reuse com-mon features from the previous layers while the Dense path can explore new features. In addition, to concatenate different scaled features, we also apply the idea of multi-stream with shortcuts between cascaded dual path residual dense block based streams. To obtain more distinct derained images, we combine the SSIM loss and perceptual loss to preserve the per-pixel similarity as well as preserving the global structures so that the deraining result is more accurate. Extensive experi-ments on both synthetic and real rainy images demonstrate that our MH-DerainNet can deliver significant improvements over several recent state-of-the-art methods. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/ICDM.2019.00073 | 2019 IEEE International Conference on Data Mining (ICDM) |
Keywords | Field | DocType |
Single image deraining, dual path residual dense block, multi-stream hybrid deraining neural detwork | Data mining,Residual,Pattern recognition,Computer science,Reuse,Concatenation,Artificial intelligence | Conference |
ISSN | ISBN | Citations |
1550-4786 | 978-1-7281-4605-8 | 1 |
PageRank | References | Authors |
0.35 | 15 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yanyan Wei | 1 | 1 | 0.35 |
| Zhao Zhang | 2 | 938 | 65.99 |
| Haijun Zhang | 3 | 495 | 37.70 |
| Richang Hong | 4 | 4791 | 176.47 |
| Meng Wang | 5 | 3094 | 167.38 |