High-Resolution Representations Network for Single Image Dehazing

Sensors

Wensheng Han¹  Hong Zhu¹  Jingsi Li²  Chenghui Qi²  Dengyin Zhang² 

[1] School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China;School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210003, China;

关键词: image dehazing;    image restoration;    deep learning;    high-resolution representations;   

DOI  :  10.3390/s22062257

来源: DOAJ

【 摘 要 】

Deep learning-based image dehazing methods have made great progress, but there are still many problems such as inaccurate model parameter estimation and preserving spatial information in the U-Net-based architecture. To address these problems, we propose an image dehazing network based on the high-resolution network, called DeHRNet. The high-resolution network originally used for human pose estimation. In this paper, we make a simple yet effective modification to the network and apply it to image dehazing. We add a new stage to the original network to make it better for image dehazing. The newly added stage collects the feature map representations of all branches of the network by up-sampling to enhance the high-resolution representations instead of only taking the feature maps of the high-resolution branches, which makes the restored clean images more natural. The final experimental results show that DeHRNet achieves superior performance over existing dehazing methods in synthesized and natural hazy images.

【 授权许可】

Unknown