CDNet: Single Image De-Hazing Using Unpaired Adversarial Training

Dudhane, Akshay; Murala, Subrahmanyam

doi:10.1109/wacv.2019.00127

Cited by 65 publications

(20 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2018, Zhang et al [28] proposed a densely connected pyramid dehazing network (DCPDN) that used a new edge-preserving densely connected encoder-decoder structure with a multilevel pyramid pooling module for estimating the transmission map. In 2019, Dudhane et al [29] proposed a dehazing network by using a cycle-consistent GAN (CDNet), which consisted of an encoder-decoder architecture that was used to estimate the transmission map and restore the hazefree scene. Qu et al [30] proposed an enhanced pix2pix dehazing network (EPDN).…”

Section: A Image Defoggingmentioning

confidence: 99%

RASWNet: An Algorithm That Can Remove All Severe Weather Features from a Degraded Image

Gao

Long

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The advanced driving assistant system (ADAS) is an important vehicle safety technology that can effectively reduce traffic accidents. This system can perceive information about the surrounding environment through in-vehicle cameras. However, these cameras are easily affected by severe weather conditions, such as those involving fog, rain, and snow. The quality of the images acquired by the system is degraded, and the function of the ADAS is thus weakened. In response to this problem, we propose a comprehensive imaging model that can represent the features of fog, rain streaks, raindrops and snowflakes in an image. Subsequently, an algorithm called RASWNet is proposed, which can remove all severe weather features from a degraded image. Based on the generative adversarial network, RASWNet combines the focus capture ability of a visual attention mechanism, the memory ability of the recurrent neural network and the feature extraction ability of the dense blocks approach. We verify the network structure through several ablation studies and use various synthetic and real images to test it. The results of these experiments show that our algorithm is not only better than the commonly used algorithms in terms of its clarity enhancement capacity but is also suitable for all severe weather conditions. INDEX TERMS Generative adversarial network, remove all severe weather features, degraded image, RASWNet, visual attention mechanism.

show abstract

Section: A Image Defoggingmentioning

confidence: 99%

RASWNet: An Algorithm That Can Remove All Severe Weather Features from a Degraded Image

Gao

Long

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Autonomous systems inevitably face the problem of the image style transfer arising from seasonal conversion, 74 varying weather conditions, 72 or day conversion. 73 In particular, it is more 130 style transfer Supervised C Johnson et al 131 style transfer O Supervised B Li et al 132 style transfer Supervised C Pix2Pix 34 style transfer O O Supervised A, E CycleGAN 24 style transfer O O Unsupervised A, D DLOW 133 style transfer 134 style transfer O Unsupervised A, C SRCNN 7 super-resolution Supervised F SRCNN 8 super-resolution Supervised F FSRCNN 135 super-resolution Supervised F Johnson et al 131 super-resolution O Supervised B SRGAN 26 super-resolution O Supervised A, F EnhanceNet 136 super-resolution O Supervised A, B, F ZSSR 137 super-resolution Unsupervised E ESRGAN 138 super-resolution O Supervised A, B, E CinCGAN 139 super-resolution O Unsupervised A, D, F Soh et al 140 super-resolution O Supervised A, C, F Gong et al 141 super-resolution O Unsupervised A, D, E DeblurGAN 27 image deblurring O Supervised A, B DeblurGAN-v2 142 image deblurring O Supervised A, E, F Dr-Net 143 image deblurring O Supervised A, E Li et al 144 image dehazing O Supervised A, B, E Cycle-Dehaze 145 image dehazing O Unsupervised A, D Kim et al 146 image dehazing O Supervised A, D, E, F CDNet 147 image dehazing O Unsupervised A, D Sharma et al 148 image dehazing O Supervised A, B, E, F Qian et al 35 image rain removal O Supervised A, B, F Li et al 149 image rain removal O Supervised A, B, F ID-CGAN 36 image rain removal O Supervised A, B, E AI-GAN 150 image rain removal O Supervised A, F Hoffman et al 71 semantic segm...…”

Section: Image Style Transfermentioning

confidence: 99%

“…Similar bidirectional GANs for dehazing have also been studied by Kim et al 146 It is difficult for the Cycle-Dehaze network to reconstruct real scene information without color distortion. Therefore, Dudhane and Murala 147 proposed the cycle-consistent generative adversarial network (CDNet), which utilized the optical model to find the haze distribution from the depth information. CDNet ensures that the fog-free scene is obtained without color distortion.…”

Section: Ll Open Accessmentioning

confidence: 99%

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

et al. 2020

View full text Add to dashboard Cite

With widespread applications of artificial intelligence (AI), the capabilities of the perception, understanding, decision-making, and control for autonomous systems have improved significantly in recent years. When autonomous systems consider the performance of accuracy and transferability, several AI methods, such as adversarial learning, reinforcement learning (RL), and meta-learning, show their powerful performance. Here, we review the learning-based approaches in autonomous systems from the perspectives of accuracy and transferability. Accuracy means that a well-trained model shows good results during the testing phase, in which the testing set shares a same task or a data distribution with the training set. Transferability means that when a well-trained model is transferred to other testing domains, the accuracy is still good. Firstly, we introduce some basic concepts of transfer learning and then present some preliminaries of adversarial learning, RL, and meta-learning. Secondly, we focus on reviewing the accuracy or transferability or both of these approaches to show the advantages of adversarial learning, such as generative adversarial networks, in typical computer vision tasks in autonomous systems, including image style transfer, image super-resolution, image deblurring/dehazing/rain removal, semantic segmentation, depth estimation, pedestrian detection, and person re-identification. We furthermore review the performance of RL and meta-learning from the aspects of accuracy or transferability or both of them in autonomous systems, involving pedestrian tracking, robot navigation, and robotic manipulation. Finally, we discuss several challenges and future topics for the use of adversarial learning, RL, and meta-learning in autonomous systems.

show abstract

“…Convolutional Neural Networks (CNNs) is one of the typical algorithms of deep learning. Many methods (Cai et al, 2016;Deng et al, 2019;Dudhane & Murala, 2019;Liu et al, 2019;Ma et al, 2019;Park et al, 2020;Ren et al, 2016;Li, Miao, et al, 2019;Zhang & Patel, 2018) based on CNNs are proposed by people to estimate the parameters of the ASM. For example, DehazeNet proposed by Cai (Cai et al, 2016) et al is the first time using CNN to directly estimate the medium transmission map from the haze image to achieve the purpose of image dehazing.…”

Section: Related Workmentioning

confidence: 99%

Single image dehazing algorithm based on pyramid mutil-scale transposed convolutional network

Wang

Duan

Yang

2020

Systems Science & Control Engineering

View full text Add to dashboard Cite

In this paper, a novel single image dehazing method based on pyramid multi-scale transposed convolutional network (MST-Net) is proposed. Conventional haze removal algorithms based on the atmospheric scattering model may lead to some problems such as incomplete dehazing and colour distortion due to the inaccurate parameter approximations or indirect image optimization and reconstruction. Therefore, we design a real end-to-end image dehazing network to directly learn the mapping relationship between hazy images and the corresponding clear images. In this network, the cascaded feature extraction blocks extract the diversified feature information of the input images by multi-channel concatenation structure, which can effectively fuse the local features of the first convolution layer into the semantic features of subsequent layers in the block. In order to reconstruct high-quality dehazed images relieving the colour distortion, we design a multi-scale transposed convolution block to gradually expand the resolution of the obtained feature maps, and introduce skip connections from the feature extraction module to supplement the detailed information of the feature map pyramid. Extensive experimental results demonstrate that the proposed method in this paper can remove the haze completely and achieve superior performance in subjective and objective evaluation over the other state-of-the-art methods.

show abstract

CDNet: Single Image De-Hazing Using Unpaired Adversarial Training

Cited by 65 publications

References 25 publications

RASWNet: An Algorithm That Can Remove All Severe Weather Features from a Degraded Image

RASWNet: An Algorithm That Can Remove All Severe Weather Features from a Degraded Image

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

Single image dehazing algorithm based on pyramid mutil-scale transposed convolutional network

Contact Info

Product

Resources

About