RI-GAN: An End-To-End Network for Single Image Haze Removal

Dudhane, Akshay; Aulakh, Harshjeet Singh; Murala, Subrahmanyam

doi:10.1109/cvprw.2019.00253

Cited by 60 publications

(21 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a public benchmark for image dehazing and beyond, the sub-dataset SOTS [ 32 ] in RESIDE containing 500 indoor images and 500 outdoor images with different haze concentration was used for testing the performance of different dehazing algorithms. The quantitative results of our model and the extra seven state-of-the-art methods tested on SOTS are displayed in Table 4 and Table 5 , where the quantitative values of some methods were collected from [ 20 , 21 , 23 ]. From Table 4 , we can see that our model ranked the third among popular dehazing methods on the indoor images of SOTS, only second to the results by GridDN [ 23 ] and EPDN [ 20 ].…”

Section: Resultsmentioning

confidence: 99%

“…Qu et al proposed the enhanced pix2pix dehazing network (EPDN), motivated by the success of the generative adversarial network (GAN) [ 20 ]. Dudhane et al further presented a generative adversarial networks with residual inception module (RIGAN) to remove haze [ 21 ]. Ren et al proposed a gated fusion network (GFN) to estimate a clear image by fusing three derived images of the original hazy image effectively [ 22 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Residual Dense Pyramid Network for Image Dehazing

Yin

Wang

Yang

2019

Entropy

View full text Add to dashboard Cite

Recently, convolutional neural network (CNN) based on the encoder-decoder structurehave been successfully applied to image dehazing. However, these CNN based dehazing methodshave two limitations: First, these dehazing models are large in size with enormous parameters, whichnot only consumes much GPU memory, but also is hard to train from scratch. Second, these models,which ignore the structural information at different resolutions of intermediate layers, cannot captureinformative texture and edge information for dehazing by stacking more layers. In this paper, wepropose a light-weight end-to-end network named the residual dense pyramid network (RDPN)to address the above problems. To exploit the structural information at different resolutions ofintermediate layers fully, a new residual dense pyramid (RDP) is proposed as a building block.By introducing a dense information fusion layer and the residual learning module, the RDP canmaximize the information flow and extract local features. Furthermore, the RDP further learnsthe structural information from intermediate layers via a multiscale pyramid fusion mechanism.To reduce the number of network parameters and to ease the training process, we use one RDPin the encoder and two RDPs in the decoder, following a multilevel pyramid pooling layer forincorporating global context features before estimating the final result. The extensive experimentalresults on a synthetic dataset and real-world images demonstrate that the new RDPN achievesfavourable performance compared with some state-of-the-art methods, e.g., the recent denselyconnected pyramid dehazing network, the all-in-one dehazing network, the enhanced pix2pixdehazing network, pixel-based alpha blending, artificial multi-exposure image fusions and thegenetic programming estimator, in terms of accuracy, run time and number of parameters. To bespecific, RDPN outperforms all of the above methods in terms of PSNR by at least 4.25 dB. The runtime of the proposed method is 0.021 s, and the number of parameters is 1,534,799, only 6% of thatused by the densely connected pyramid dehazing network.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Novel Residual Dense Pyramid Network for Image Dehazing

Yin

Wang

Yang

2019

Entropy

View full text Add to dashboard Cite

show abstract

“…Zhang et al also addressed the end-to-end dehazing problem under a deep learning based densely connected pyramid dehazing network [ 34 ]. Approaches using generative adversarial networks have also been studied in recent years [ 37 , 38 , 39 , 40 ] Although these methods are capable of recovering satisfying results in daytime, their performances on nighttime dehazing are quite limited. In addition, learning based methods, especially the data-driven deep learning based approaches rely on the sufficient training data.…”

Section: Related Workmentioning

confidence: 99%

SIDE—A Unified Framework for Simultaneously Dehazing and Enhancement of Nighttime Hazy Images

Guo

Shi

2020

Sensors

View full text Add to dashboard Cite

Single image dehazing is a difficult problem because of its ill-posed nature. Increasing attention has been paid recently as its high potential applications in many visual tasks. Although single image dehazing has made remarkable progress in recent years, they are mainly designed for haze removal in daytime. In nighttime, dehazing is more challenging where most daytime dehazing methods become invalid due to multiple scattering phenomena, and non-uniformly distributed dim ambient illumination. While a few approaches have been proposed for nighttime image dehazing, low ambient light is actually ignored. In this paper, we propose a novel unified nighttime hazy image enhancement framework to address the problems of both haze removal and illumination enhancement simultaneously. Specifically, both halo artifacts caused by multiple scattering and non-uniformly distributed ambient illumination existing in low-light hazy conditions are considered for the first time in our approach. More importantly, most current daytime dehazing methods can be effectively incorporated into nighttime dehazing task based on our framework. Firstly, we decompose the observed hazy image into a halo layer and a scene layer to remove the influence of multiple scattering. After that, we estimate the spatially varying ambient illumination based on the Retinex theory. We then employ the classic daytime dehazing methods to recover the scene radiance. Finally, we generate the dehazing result by combining the adjusted ambient illumination and the scene radiance. Compared with various daytime dehazing methods and the state-of-the-art nighttime dehazing methods, both quantitative and qualitative experimental results on both real-world and synthetic hazy image datasets demonstrate the superiority of our framework in terms of halo mitigation, visibility improvement and color preservation.

show abstract

“…Recently, they concentrate their attention on deep learning especially GAN to explore how well it performs the task of haze removal, inspired by the outstanding results of CNN and GAN in high-level vi-sion tasks, such as image classification, image understanding, and deblurring, etc. [2]- [28]. In fact, by default, a deep learning-based approach is always superior to the classical approaches, as it uses deep features rather than superficial features.…”

Section: Related Workmentioning

confidence: 99%

“…Dudhane et al [28] proposed an end-to-end GAN that outperformed other existing algorithms through conducting experiments on NTIRE 2019 dehazing challenge dataset [29], D-Hazy [30] and indoor SOTS [23] datasets for single image dehazing.…”

Section: Related Workmentioning

confidence: 99%

Single Image Dehazing: An Analysis on Generative Adversarial Network

Khatun¹,

Haque²,

Basri³

et al. 2020

JCC

View full text Add to dashboard Cite

Haze is a very common phenomenon that degrades or reduces visibility. It causes various problems where high-quality images are required such as traffic and security monitoring. So haze removal from scenes is an immediate demand for clear vision. Recently, in addition to the conventional dehazing mechanisms, different types of deep generative adversarial networks (GAN) are applied to suppress the noise and improve the dehazing performance. But it is unclear how these algorithms would perform on hazy images acquired "in the wild" and how we could gauge the progress in the field. To bridge this gap, this presents a comprehensive study on three single image dehazing state-of-the-art GAN models, such as AOD-Net, cGAN, and DHSGAN. We have experimented using benchmark dataset consisting of both synthetic and real-world hazy images. The obtained results are evaluated both quantitatively and qualitatively. Among these techniques, the DHSGAN gives the best performance.

show abstract

RI-GAN: An End-To-End Network for Single Image Haze Removal

Cited by 60 publications

References 31 publications

A Novel Residual Dense Pyramid Network for Image Dehazing

A Novel Residual Dense Pyramid Network for Image Dehazing

SIDE—A Unified Framework for Simultaneously Dehazing and Enhancement of Nighttime Hazy Images

Single Image Dehazing: An Analysis on Generative Adversarial Network

Contact Info

Product

Resources

About