| Autor: |
Xinshan, Zhu, Shuoshi, Li, Yongdong, Gan, Yun, Zhang, Biao, Sun |
| Rok vydání: |
2021 |
| Zdroj: |
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 30 |
| ISSN: |
1941-0042 |
| Popis: |
Single image dehazing is an important but challenging computer vision problem. For the problem, an end-to-end convolutional neural network, named multi-stream fusion network (MSFNet), is proposed in this paper. MSFNet is built following the encoder-decoder network structure. The encoder is a three-stream network to produce features at three resolution levels. Residual dense blocks (RDBs) are used for feature extraction. The resizing blocks serve as bridges to connect different streams. The features from different streams are fused in a full connection manner by a feature fusion block, with stream-wise and channel-wise attention mechanisms. The decoder directly regresses the dehazed image from coarse to fine by the use of RDBs and the skip connections. To train the network, we design a generalized smooth L |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
