Single Image Dehazing with a Generic Model-Agnostic Convolutional Neural Network

Liu, Zheng; Xiao, Botao; Alrabeiah, Muhammad; Wang, Keyan; Chen, Jun

doi:10.1109/lsp.2019.2910403

Cited by 106 publications

(40 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dehazed results generated by GMAN [35] and the proposed DRHNet are most similar to the GT. But the quantitative evaluation score of DRHNet is higher than GMAN [35]. Therefore, the performance of DRHNet is better than GMAN [35].…”

Section: ) Quantitative Evaluation For Synthetic Imagesmentioning

confidence: 65%

“…But the quantitative evaluation score of DRHNet is higher than GMAN [35]. Therefore, the performance of DRHNet is better than GMAN [35].…”

Section: ) Quantitative Evaluation For Synthetic Imagesmentioning

confidence: 91%

“…As shown in Table 1, we compare the proposed DRHNet with several state-of-the-art image dehazing algorithms quantitatively, including two representative traditional algorithms, i.e., Dark-Channel Prior (DCP) [7] and Boundary Constrained Context Regularization (BCCR) [32], and three latest traditional image dehazing algorithms, i.e., Gradient Residual Minimization (GRM) [33], Color Attenuation Prior (CAP) [8], Non-local Image Dehazing (NLD) [34], and four learning-based methods, i.e., DehazeNet [12], Multiscale CNN (MSCNN) [15], All-in-One Dehazing Network (AOD-Net) [13] and Generic model-agnostic convolutional neural network (GMAN) [35]. The quantitative evaluation was performed on the three testing sets, which include 500 synthetic indoor images in SOTS [17], 500 synthetic outdoor images in SOTS [17], and 10 synthetic images in (HSTS) [17].…”

Section: ) Quantitative Evaluation For Synthetic Imagesmentioning

confidence: 99%

See 2 more Smart Citations

Deep Residual Haze Network for Image Dehazing and Deraining

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Image dehazing on a hazy image aims to remove the haze and make the image scene clear, which attracts more and more research interests in recent years. Most existing image dehazing methods use a classic atmospheric scattering model and natural image priors to remove the image haze. In this paper, we propose an end-to-end image dehazing model termed as DRHNet (Deep Residual Haze Network), which restores the haze-free image by subtracting the learned negative residual map from the hazy image. Specifically, DRHNet proposes a context-aware feature extraction module to aggregate the contextual information effectively. Furthermore, it proposes a novel nonlinear activation function termed as RPReLU (Reverse Parametric Rectified Linear Unit) to improve its representation ability and to accelerate its convergence. Extensive experiments demonstrate that DRHNet outperforms state-of-the-art methods both quantitatively and qualitatively. In addition, experiments on image deraining task show that DRHNet can also serve for image deraining. INDEX TERMS Image dehazing, image deraining, negative residual map, context-aware feature extraction, reverse parametric rectified linear unit (RPReLU).

show abstract

Section: ) Quantitative Evaluation For Synthetic Imagesmentioning

confidence: 65%

“…But the quantitative evaluation score of DRHNet is higher than GMAN [35]. Therefore, the performance of DRHNet is better than GMAN [35].…”

Section: ) Quantitative Evaluation For Synthetic Imagesmentioning

confidence: 91%

Section: ) Quantitative Evaluation For Synthetic Imagesmentioning

confidence: 99%

See 1 more Smart Citation

Deep Residual Haze Network for Image Dehazing and Deraining

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Those methods can be divided into two catagories. They either use traditional image enhancement techniques or prior-based computational models [6], [7], [12]- [14], [16], [24], [29], [30], [32], [36]- [44], [48], or learn a deep neural network for recovering the haze-free images [7], [23], [25], [26], [33], [50]. These methods cannot be directly applied to the nighttime dehazing problem due to its complex imaging conditions and the ineffective use of daytime image priors.…”

Section: Related Workmentioning

confidence: 99%

Integrating Haze Density Features for Fast Nighttime Image Dehazing

Lou

Yang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

To date, much progress has been achieved on daytime image dehazing, yet the nighttime dehazing problem is still not well addressed. Different from the imaging conditions in the daytime, the ambient illumination in the nighttime hazy scene is usually not globally isotropic due to the non-uniform incident lights from multiple artificial light sources. Currently, almost all the existing nighttime dehazing methods use a certain kind of image priors, whereby these spatial filtering based priors are not widely applicable in nighttime hazy scenes. For example, the maximum reflectance prior (MRP) cannot handle the dark regions well and the dark channel prior (DCP) is not valid in the light source regions. In this paper, we propose an efficient and fast method for nighttime image dehazing. By exploring the visual properties of hazy images, we construct an effective linear model to build the connection between the transmission and multiple haze-relevant features. Towards solving this model, a data-driven approach is adopted to learn the unknown coefficients. Operating on the pixel level, this novel approach requires no further refinement of transmission map as used in those prior-based methods. In addition, aiming at solving the problem of halo effect around the light sources caused by MRP, we introduce a color-dependant MRP method for color correction. We demonstrate the effectiveness of our method on a number of experiments compared to the state-of-the-art nighttime dehazing methods.

show abstract

“…The purpose of image dehazing is to reduce or remove the effect of haze for more effective subsequent research. In recent years, there have been many studies on image dehazing [1]- [6]. He et al [7] proposed a dark channel prior method, which achieved good dehazing effects, but the soft matting method used had problems of low efficiency and a large number of calculations.…”

Section: Introductionmentioning

confidence: 99%

Multilevel Image Dehazing Algorithm Using Conditional Generative Adversarial Networks

2020

View full text Add to dashboard Cite

In recent years, the hazy weather in China occurs frequently, and image dehazing has gradually become a research hotspot. To improve the dehazing effect of the hazy images, this paper has proposed a multilevel image dehazing algorithm using conditional generative adversarial networks (CGAN). The hazy image is used to generate the composed image K jointly estimated by a transmission map and atmospheric light value through a generator network, and a dehazed image is calculated through an improved atmospheric scattering model. The generator network and the joint discriminator network are subjected to adversarial training and reconstruction constraints. The experimental results show that the proposed method achieved good dehazing effect in synthetic hazy images and real hazy images, and is ahead of other advanced dehazing methods in subjective evaluation and objective evaluation. INDEX TERMS CGAN, jointly estimate, atmospheric scattering model, image dehazing.

show abstract

Single Image Dehazing with a Generic Model-Agnostic Convolutional Neural Network

Cited by 106 publications

References 20 publications

Deep Residual Haze Network for Image Dehazing and Deraining

Deep Residual Haze Network for Image Dehazing and Deraining

Integrating Haze Density Features for Fast Nighttime Image Dehazing

Multilevel Image Dehazing Algorithm Using Conditional Generative Adversarial Networks

Contact Info

Product

Resources

About