Unsupervised Dark-Channel Attention-Guided CycleGAN for Single-Image Dehazing
1
National Key Laboratory of Fundamental Science on Synthetic Vision, Chengdu 610000, China
2
School of Computer Science, Sichuan University, Chengdu 610000, China
3
School of Aeronautics and Astronautics, Sichuan University, Chengdu 610000, China
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(21), 6000; https://doi.org/10.3390/s20216000
Received: 3 September 2020
/
Revised: 12 October 2020
/
Accepted: 13 October 2020
/
Published: 23 October 2020
(This article belongs to the Section Sensing and Imaging)
In this paper, we propose a new unsupervised attention-based cycle generative adversarial network to solve the problem of single-image dehazing. The proposed method adds an attention mechanism that can dehaze different areas on the basis of the previous generative adversarial network (GAN) dehazing method. This mechanism not only avoids the need to change the haze-free area due to the overall style migration of traditional GANs, but also pays attention to the different degrees of haze concentrations that need to be changed, while retaining the details of the original image. To more accurately and quickly label the concentrations and areas of haze, we innovatively use training-enhanced dark channels as attention maps, combining the advantages of prior algorithms and deep learning. The proposed method does not require paired datasets, and it can adequately generate high-resolution images. Experiments demonstrate that our algorithm is superior to previous algorithms in various scenarios. The proposed algorithm can effectively process very hazy images, misty images, and haze-free images, which is of great significance for dehazing in complex scenes.
View Full-Text
Keywords:
dehazing; GAN; attention; dark channel
▼
Show Figures
Figure 1
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
MDPI and ACS Style
Chen, J.; Wu, C.; Chen, H.; Cheng, P. Unsupervised Dark-Channel Attention-Guided CycleGAN for Single-Image Dehazing. Sensors 2020, 20, 6000. https://doi.org/10.3390/s20216000
AMA Style
Chen J, Wu C, Chen H, Cheng P. Unsupervised Dark-Channel Attention-Guided CycleGAN for Single-Image Dehazing. Sensors. 2020; 20(21):6000. https://doi.org/10.3390/s20216000
Chicago/Turabian StyleChen, Jiahao, Chong Wu, Hu Chen, and Peng Cheng. 2020. "Unsupervised Dark-Channel Attention-Guided CycleGAN for Single-Image Dehazing" Sensors 20, no. 21: 6000. https://doi.org/10.3390/s20216000
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
