Image dehazing based on double branch convolution and detail enhancement | Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University

Open Access

表1

各算法在混合数据集Haze4K中PSNR和SSIM的值

方法	PSNR	SSIM
DCP[4](TPAMI 2010)	14.01	0.760
DehazeNet[7](TIP 2016)	19.12	0.840
AOD-Net[9](ICCV 2017)	17.15	0.830
FFA-Net[10](AAAI 2020)	26.96	0.950
MSBDN[12](CVPR 2020)	22.99	0.850
DMT-Net[13](ACMMM 2021)	28.53	0.960
gUnet-T[11](CVPR 2022)	31.60	0.984
DBDENet(本文)	32.04	0.984

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.