Weifeng Zhong, Jing Zhao. Image Defogging Algorithm Based on Generative Adversarial Network[J]. Laser & Optoelectronics Progress, 2022, 59(4): 0415007
- Laser & Optoelectronics Progress
- Vol. 59, Issue 4, 0415007 (2022)
Fig. 1. Flow chart of GAN
Fig. 2. Schematic of CycleGAN
Fig. 3. Schematic of CycleGAN structure
Fig. 4. U-Net structure
Fig. 5. Generator structure
Fig. 6. Errors in 20-layer and 56-layer network training. (a) Training error; (b) test error
Fig. 7. Weighted residual module
Fig. 8. Experimental results of different algorithms on foggy trees. (a) Original picture; (b) AODNet algorithm; (c) DehazeNet algorithm; (d) FFANet algorithm; (e) GCANet algorithm; (f) improved CycleGAN algorithm
Fig. 9. Experimental results of different algorithms on foggy scenes. (a) Original picture; (b) AODNet algorithm; (c) DehazeNet algorithm; (d) FFANet algorithm; (e) GCANet algorithm; (f) improved CycleGAN algorithm
|
Table 1. Size information of generator
|
Table 2. Evaluation indexes of Fig.8
|
Table 3. Evaluation indexes of Fig.9
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20