Semi-Supervised image dehazing network

• Published in: The Visual computer Vol. 38; no. 6; pp. 2041 - 2055
• Main Authors: An, Shunmin, Huang, Xixia, Wang, Le, Wang, Linling, Zheng, Zhangjing
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2022; Springer Nature B.V
• Subjects: Artificial Intelligence; Coding; Computer Graphics; Computer Science; Datasets; Image Processing and Computer Vision; Knowledge; Methods; Neural networks; Original Article; Supervised branch; Reconstruction loss; Unsupervised loss; Unsupervised branch; End-to-end; Semi-supervised
• ISSN: 0178-2789; 1432-2315
• DOI: 10.1007/s00371-021-02265-5

A semi-supervised image dehazing network was proposed which consists of the supervised branch and the unsupervised branch. In the supervision branch, the encoding–decoding neural network is used as the network structure, and the network is constrained by the supervision loss. In the unsupervised branch, two similar sub-networks are used to estimate the transmission map and atmospheric light, and the unsupervised loss is constructed through prior knowledge to constrain the unsupervised branch. In the semi-supervised image dehazing network, the supervised branch and the unsupervised branch will output dehazing result, respectively. Then by minimizing the reconstruction loss between the two images, the supervised and unsupervised branches are constrained to make the network more generalizable. The entire semi-supervised image dehazing network is trained in an end-to-end manner, and the supervised and unsupervised branch shares weights in the encoding part. Extensive experimental results show that the proposed method has good performance in image dehazing compared with six advanced dehazing methods.