Unsupervised single image dehazing with generative adversarial network

Ren, Wei; Zhou, Li; Chen, Jie

doi:10.1007/s00530-021-00852-z

Cited by 11 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach involves employing a haze-generation GAN to synthesize hazy images from real-world images, followed by utilizing a haze-removal GAN network for the dehazing process. Ren et al proposed an unsupervised dehazing algorithm based on a GAN [36], which employs two discriminators to consider global and local information along with a dark-channel attention mechanism. While most of the haze can be removed using this approach, some residual haze may remain.…”

Section: Related Workmentioning

confidence: 99%

Remote Sensing Image Dehazing through an Unsupervised Generative Adversarial Network

Zhao,

Yin,

Zhong

et al. 2023

Sensors

View full text Add to dashboard Cite

The degradation of visual quality in remote sensing images caused by haze presents significant challenges in interpreting and extracting essential information. To effectively mitigate the impact of haze on image quality, we propose an unsupervised generative adversarial network specifically designed for remote sensing image dehazing. This network includes two generators with identical structures and two discriminators with identical structures. One generator is focused on image dehazing, while the other generates images with added haze. The two discriminators are responsible for distinguishing whether an image is real or generated. The generator, employing an encoder–decoder architecture, is designed based on the proposed multi-scale feature-extraction modules and attention modules. The proposed multi-scale feature-extraction module, comprising three distinct branches, aims to extract features with varying receptive fields. Each branch comprises dilated convolutions and attention modules. The proposed attention module includes both channel and spatial attention components. It guides the feature-extraction network to emphasize haze and texture within the remote sensing image. For enhanced generator performance, a multi-scale discriminator is also designed with three branches. Furthermore, an improved loss function is introduced by incorporating color-constancy loss into the conventional loss framework. In comparison to state-of-the-art methods, the proposed approach achieves the highest peak signal-to-noise ratio and structural similarity index metrics. These results convincingly demonstrate the superior performance of the proposed method in effectively removing haze from remote sensing images.

show abstract

Section: Related Workmentioning

confidence: 99%

Remote Sensing Image Dehazing through an Unsupervised Generative Adversarial Network

Zhao,

Yin,

Zhong

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Due to the limitations on the accurate estimation of transmission and/or air light, researchers have developed deep models to be trained with hazy and clear image pairs. Therefore, many learning based methods based on Convolutional Neural Network (CNN) [9][10][11][12][13], Generative Adversarial Networks [14,15], Vision Transformers [16][17][18] structures have been developed. By this way, several hazy image datasets were created and provided as open source [2,19,20,21,22].…”

Section: Introductionmentioning

confidence: 99%

Near real-time hybrid dehazing based on the estimation of air light with deep learning

Çimtay

2023

Preprint

View full text Add to dashboard Cite

Haze which can be created by natural or synthetic factors, degrades the visual quality and human sight distance. Visible objects become scarcely visible or invisible. The physics of the degrading function due to haze has been modelled by Atmospheric Light Scattering (ALS) Model. Therefore, from a single hazy image, by using proper methods, it is possible to recover the original scene. In dehazing methods which solve the ALS function, there are basically two steps. First one is the estimation of the air light present at the time of the image capturing and the second step is the estimation of transmission of the corresponding scene. One of the most effective method which is used for air light estimation is QuadTree decomposition. For this method, tests show that the most amount of the dehazing time is consumed to estimate the air light. For the case of High Definition (HD) imagery, the estimation of air light consumes huge time. Therefore, it cannot be possible to achieve a real time or near real time dehazing on traditional hardware. In this study, a novel convolutional neural network model is developed to estimate the air light directly from the hazy image quickly. The estimated air light then can be used with Atmospheric Light Scattering model to handle the recovered image. Results show that the time cost is reduced by 56.0% and 65% for image resolutions of (640x480) and (1920x1080) compared to the QuadTree Decomposition method used in ALS based dehazing methods, without losing the visual quality of the dehazed image.

show abstract

“…Occluded and distorted images due to rain can make these computer vision applications less effective or lose their original functionality. Based on these demands, use computer programs such as deraining [1] and dehazing [2,3] to make images clearer have developed rapidly in recent years. With the development of deep learning, deep learning-based derain network has been widely used.…”

mentioning

confidence: 99%

Import vertical characteristic of rain streak for single image deraining

Zhang

Ding

et al. 2022

Multimedia Systems

View full text Add to dashboard Cite

Recently, deep convolutional neural networks show good effect for single image deraining. These networks always adopt the conventional convolution method to extract features, which may neglect the characteristic of rain streak. A novelty vertical module is proposed to focus on the vertical characteristic of rain streak. Such module uses 1 × X convolution kernel to extract the vertical information of rain streaks and a X × X convolution kernel to keep relative location information. Use this module in the front of deraining network can better detach rain streaks from background. In addition, the contrastive learning is employed to improve the performance of the model. Extensive experimental results demonstrated the superiority of the deraining methods with the proposed methods in comparison with the base ones.

show abstract

Unsupervised single image dehazing with generative adversarial network

Cited by 11 publications

References 38 publications

Remote Sensing Image Dehazing through an Unsupervised Generative Adversarial Network

Remote Sensing Image Dehazing through an Unsupervised Generative Adversarial Network

Near real-time hybrid dehazing based on the estimation of air light with deep learning

Import vertical characteristic of rain streak for single image deraining

Contact Info

Product

Resources

About