To remove image haze and make haze image scene clear, we proposed an image dehazing network based on multi-scale feature extraction (MSFNet) in this paper. The MSFNet first directly performs feature extraction on hazy images with three different resolutions to obtain fine feature maps and concatenates them with the rough feature maps extracted in the downsampling process for fusing and obtaining richer image information. Then, the fused feature maps are put into a network module composed of ResNeXt building blocks for network learning. Next, the feature maps extracted by upsampling are sequentially concatenated with the feature maps learned by the ResNeXt module for obtaining the residual image. Finally, the learned residual image is added to the input hazy image to obtain the image dehazing result. The experimental results on the SOTS dataset show that the MSFNet improves effectiveness of image dehazing.
Image Dehazing Network Based on Multi-scale Feature Extraction
Smart Innovation, Systems and Technologies
Advances in Smart Vehicular Technology, Transportation, Communication and Applications ; Chapter : 39 ; 391-399
2021-11-30
9 pages
Article/Chapter (Book)
Electronic Resource
English
Image Dehazing Network Based on Multi-scale Feature Extraction
TIBKAT | 2022
|Springer Verlag | 2021
|Single Image Dehazing of Railway Images via Multi-scale Residual Networks
Springer Verlag | 2020
|Single Image Dehazing of Railway Images via Multi-scale Residual Networks
British Library Conference Proceedings | 2020
|