基于改进CycleGAN的多失真类型水下图像增强

吕振鸣,董绍江,夏宗佑,牟小燕,王明权

Multi-distortion type underwater image enhancement based on improved CycleGAN

Zhenming LV,Shaojiang DONG,Zongyou XIA,Xiaoyan MOU,Mingquan WANG

表 2 几种算法在EUVP和UIEB中有雾失真图像上的定量评估结果

Tab.2 Quantitative evaluation results of several algorithms for foggy distorted images on EUVP and UIEB

算法 PSNR SSIM UIQM UCIQE CLAHE 18.1837 0.7487 2.7732 0.3827 UDCP 17.0665 0.7716 2.6927 0.3756 Retinex 20.4668 0.8093 2.6793 0.3958 IBLA 16.7103 0.7272 3.4714 0.4026 CycleGAN 19.5113 0.7431 3.3523 0.4388 FUnIE-GAN 16.5819 0.6602 3.2576 0.4182 LANet 22.0119 0.8549 3.5531 0.4494 SCEIR 23.2234 0.8529 3.5802 0.4473 MGCycleGAN 24.1670 0.8763 3.6301 0.4562