当前位置: X-MOL 学术J. Electron. Imaging › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
DFBDehazeNet: an end-to-end dense feedback network for single image dehazing
Journal of Electronic Imaging ( IF 1.1 ) Pub Date : 2021-05-01 , DOI: 10.1117/1.jei.30.3.033004
Mengyan Guo 1 , Bo Huang 1 , Juan Zhang 1 , Feng Wang 1 , Yan Zhang 1 , Zhijun Fang 1
Affiliation  

The feedback mechanism method of simulating the biological vision system has not been widely used in deep learning dehazing algorithms. To alleviate the difficulty of feature interaction, we combine the feedback mechanism with dense skip connections to fuse features of different levels in a dehazing network. Inspired by the feedback network in which previous network layers can have access to rich information processed by the following network layers, we propose an end-to-end dense feedback network (DFBDehazeNet) for single image dehazing that implements the feedback mechanism using hidden states of constrained RNN. The low-level hazy feature information can be continuously corrected by the high-level feature information obtained from the dense feedback block via the recurrent feedback connection. The top-down feedback mechanism is adopted in DFBDehazeNet to refine the low-level hazy feature information, thereby achieving a powerful image restoration effect. The ablation experiment proves that the iterative structure of DFBDehazeNet and the projection unit play an important role in removing haze from images. The experimental results show that the results of image haze removal are superior to the great majority of existing methods both qualitatively and quantitatively.

中文翻译:

DFBDehazeNet:用于单图像去雾的端到端密集反馈网络

模拟生物视觉系统的反馈机制方法尚未在深度学习除雾算法中广泛使用。为了减轻特征交互的难度,我们将反馈机制与密集跳过连接相结合,以融合除雾网络中不同级别的特征。受反馈网络的启发,在该网络中,先前的网络层可以访问由后续网络层处理的丰富信息,因此,我们提出了一种用于单图像去雾的端到端密集反馈网络(DFBDehazeNet),该网络使用隐藏的状态来实现反馈机制。受约束的RNN。可以通过递归反馈连接通过从密集反馈块获得的高级特征信息来连续校正低级模糊特征信息。DFBDehazeNet中采用了自顶向下的反馈机制,以细化低级模糊特征信息,从而实现了强大的图像恢复效果。消融实验证明,DFBDehazeNet和投影单元的迭代结构在去除图像中的雾霾方面起着重要作用。实验结果表明,图像雾度去除的结果在质量和数量上均优于大多数现有方法。
更新日期:2021-05-11
down
wechat
bug