Multi-patch and Multi-scale Hierarchical Aggregation Network for Fast Nonhomogeneous ImageDehazing

Abstract

Despite dehazing algorithms based on convolutional neural networks have made tremendous progress in synthetic uniform hazy datasets,they still perform poorly on real nonhomogeneous hazy images.In order to achieve fast and effective nonhomogeneous image dehazing,we propose a multi-patch and multi-scale hierarchical aggregation network (MPSHAN),which fuses multi-patch local information and multi-scale global information.Secondly,we propose a hierarchical fusion module (HFM),which not only decouples residual fusion to achieve richer non-linear feature expression,but also improves the feature fusion qua-lity at key locations through the channel attention mechanism.At the same time,dilated convolution is used on hierarchies to obtain multi-scale information,which enhances feature maps to optimize the fusion effect.In addition,in the loss function,we add frequency domain loss to restore better edge quality.The experimental results show that the proposed algorithm has good robustness on nonhomogeneous hazy images,and the average processing time of 1 200×1 600 high-resolution images is only 0.044 s.Compared with other dehazing algorithms,it achieves a better balance between image dehazing effect and running time.

Keywords

• multi-patch|multi-scale|hierarchical fusion module|attention mechanism|dilated convolution|image dehazing