Proximal Dehaze-Net: A Prior Learning-Based Deep Network for Single Image Dehazing

Dong, Yingshan; Sun, Jian

doi:10.1007/978-3-030-01234-2_43

Cited by 251 publications

(132 citation statements)

References 34 publications

Supporting

Mentioning

132

Contrasting

Order By: Relevance

“…This technique has been widely utilized in various computer vision tasks and has been substantiated to be effective in compressed sensing, dehazing, deconvolution, etc. [44,45,53]. The proposed network is a structure of K stages implementing K iterations in the iterative algorithm for solving Eq.…”

Section: Ms/hs Fusion Netmentioning

confidence: 99%

Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net

Xie

Zhou

Zhao

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

234

138

View full text Add to dashboard Cite

Hyperspectral imaging can help better understand the characteristics of different materials, compared with traditional image systems. However, only high-resolution multispectral (HrMS) and low-resolution hyperspectral (LrHS) images can generally be captured at video rate in practice. In this paper, we propose a model-based deep learning approach for merging an HrMS and LrHS images to generate a high-resolution hyperspectral (HrHS) image. In specific, we construct a novel MS/HS fusion model which takes the observation models of low-resolution images and the lowrankness knowledge along the spectral mode of HrHS image into consideration. Then we design an iterative algorithm to solve the model by exploiting the proximal gradient method. And then, by unfolding the designed algorithm, we construct a deep network, called MS/HS Fusion Net, with learning the proximal operators and model parameters by convolutional neural networks. Experimental results on simulated and real data substantiate the superiority of our method both visually and quantitatively as compared with state-of-the-art methods along this line of research.

show abstract

Section: Ms/hs Fusion Netmentioning

confidence: 99%

Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net

Xie

Zhou

Zhao

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

234

138

View full text Add to dashboard Cite

show abstract

“…Recently, Zhang et al [53] proposed a method that uses CNNs to jointly estimate t and A, which outperforms previous approaches by a large margin. Ren et al [34] and Li et al [24] proposed method to directly estimate J(x) without explicitly estimating t and A. Yang et al [50] proposed a method that integrates CNNs to classical prior-based method.…”

Section: Related Workmentioning

confidence: 99%

“…Following the same experimental protocols used by previous studies, we trained and tested the proposed DuRN-P using the training and test subsets (300 and 200 grayscale images) of the BSD-grayscale dataset [27]. Table 2: Results for additive Gaussian noise removal on BSD200-grayscale and noise levels (30,50,70). The numbers are PSNR/SSIM.…”

Section: Noise Removalmentioning

confidence: 99%

Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration

Liu

Suganuma

Sun

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

207

View full text Add to dashboard Cite

In this paper, we study design of deep neural networks for tasks of image restoration. We propose a novel style of residual connections dubbed "dual residual connection", which exploits the potential of paired operations, e.g., upand down-sampling or convolution with large-and smallsize kernels. We design a modular block implementing this connection style; it is equipped with two containers to which arbitrary paired operations are inserted. Adopting the "unraveled" view of the residual networks proposed by Veit et al., we point out that a stack of the proposed modular blocks allows the first operation in a block interact with the second operation in any subsequent blocks. Specifying the two operations in each of the stacked blocks, we build a complete network for each individual task of image restoration. We experimentally evaluate the proposed approach on five image restoration tasks using nine datasets. The results show that the proposed networks with properly chosen paired operations outperform previous methods on almost all of the tasks and datasets.

show abstract

“…For example, He et al [7] and Berman et al [10] respectively proposed a dark channel prior and a haze-line prior. Recently, many learning-based methods using neural networks have also been proposed [11]- [15].…”

Section: Scattering Removalmentioning

confidence: 99%

Simultaneous Estimation of Object Region and Depth in Participating Media Using a ToF Camera

Fujimura

Sonogashira

Iiyama

2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Three-dimensional (3D) reconstruction and scene depth estimation from 2-dimensional (2D) images are major tasks in computer vision. However, using conventional 3D reconstruction techniques gets challenging in participating media such as murky water, fog, or smoke. We have developed a method that uses a continuous-wave time-of-flight (ToF) camera to estimate an object region and depth in participating media simultaneously. The scattered light observed by the camera is saturated, so it does not depend on the scene depth. In addition, received signals bouncing off distant points are negligible due to light attenuation, and thus the observation of such a point contains only a scattering component. These phenomena enable us to estimate the scattering component in an object region from a background that only contains the scattering component. The problem is formulated as robust estimation where the object region is regarded as outliers, and it enables the simultaneous estimation of an object region and depth on the basis of an iteratively reweighted least squares (IRLS) optimization scheme. We demonstrate the effectiveness of the proposed method using captured images from a ToF camera in real foggy scenes and evaluate the applicability with synthesized data.

show abstract

Proximal Dehaze-Net: A Prior Learning-Based Deep Network for Single Image Dehazing

Cited by 251 publications

References 34 publications

Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net

Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net

Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration

Simultaneous Estimation of Object Region and Depth in Participating Media Using a ToF Camera

Contact Info

Product

Resources

About