NTIRE 2020 Challenge on NonHomogeneous Dehazing

Ancuti, Cosmin; Vasluianu, Florin-Alexandru; Timofte, Radu; Liu, Jing; Wu, Haiyan; Xie, Yuan; Qu, Yanyun; Ma, Lizhuang; Huang, Ziling; Deng, Qili; Chao, Ju-Chin; Yang, Tsung-Shan; Chen, Peng-Wen; Hsu, Po-Min; Liao, Tzu-Yi; Sun, Chung-En; Wu, Pei-Yuan; Do, Jeonghyeok; Park, Jong-Min; Kim, Munchurl; Metwaly, Kareem; Li, Xuelu; Guo, Tiantong; Monga, Vishal; Yu, Mingzhou; Cherukuri, Venkateswararao; Chuang, Shiue-Yuan; Lin, Tong‐Hong; Lee, David; Chang, Jerome; Wang, Zhan-Han; Chang, Yu-Bang; Lin, Chang-Hong; Dong, Yu; Zhou, Hongyu; Kong, Xiangzhen; Das, Sourya Dipta; Dutta, Saikat; Zhao, Xuan; Ouyang, Bing; Estrada, Dennis; Wang, Meiqi; Su, Tianqi; Chen, Siyi; Sun, Bangyong; Dravo, Vincent Jacob Whannou de; Yu, Zhe; Narang, Pratik; Mehra, Aryan; Raghunath, Navaneeth; Mandal, Murari

doi:10.1109/cvprw50498.2020.00253

Cited by 73 publications

(29 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, we implement our method on real-world dehazing benchmarks with the O-HAZE dataset [ 51 ] utilized in NTIRE2018 Dehazing Challenge [ 52 ], DENSE-HAZE dataset [ 53 ] utilized in NTIRE2019 Dehazing Challenge [ 54 ] and NH-HAZE dataset [ 55 ] utilized in the NTIRE2020 Dehazing Challenge [ 56 ]. O-HAZE, DENSE-HAZE and NH-HAZE contain 45 outdoor hazy images, 55 dense hazy images and 55 nonhomogeneous hazy images with their corresponding ground truth, respectively.…”

Section: Resultsmentioning

confidence: 99%

Residual Spatial and Channel Attention Networks for Single Image Dehazing

Jiang

Zhao

Zhu

et al. 2021

Sensors

View full text Add to dashboard Cite

Single image dehazing is a highly challenging ill-posed problem. Existing methods including both prior-based and learning-based heavily rely on the conceptual simplified atmospheric scattering model by estimating the so-called medium transmission map and atmospheric light. However, the formation of haze in the real world is much more complicated and inaccurate estimations further degrade the dehazing performance with color distortion, artifacts and insufficient haze removal. Moreover, most dehazing networks treat spatial-wise and channel-wise features equally, but haze is practically unevenly distributed across an image, thus regions with different haze concentrations require different attentions. To solve these problems, we propose an end-to-end trainable densely connected residual spatial and channel attention network based on the conditional generative adversarial framework to directly restore a haze-free image from an input hazy image, without explicitly estimation of any atmospheric scattering parameters. Specifically, a novel residual attention module is proposed by combining spatial attention and channel attention mechanism, which could adaptively recalibrate spatial-wise and channel-wise feature weights by considering interdependencies among spatial and channel information. Such a mechanism allows the network to concentrate on more useful pixels and channels. Meanwhile, the dense network can maximize the information flow along features from different levels to encourage feature reuse and strengthen feature propagation. In addition, the network is trained with a multi-loss function, in which contrastive loss and registration loss are novel refined to restore sharper structures and ensure better visual quality. Experimental results demonstrate that the proposed method achieves the state-of-the-art performance on both public synthetic datasets and real-world images with more visually pleasing dehazed results.

show abstract

Section: Resultsmentioning

confidence: 99%

Residual Spatial and Channel Attention Networks for Single Image Dehazing

Jiang

Zhao

Zhu

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…3) NH-HAZE: NH-HAZE dataset [37] was proposed in the NTIRE2020 Image Dehazing Challenge [42], which is a nonhomogeneous realistic dataset that contains 55 outdoor scenes. In NH-HAZE, the haze was be introduced in the scene by using a professional haze generator, which can simulates the real conditions of hazy scenes.…”

Section: A Datasetmentioning

confidence: 99%

Efficient and Accurate Multi-Scale Topological Network for Single Image Dehazing

Fang

et al. 2022

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Single image dehazing is a challenging ill-posed problem that has drawn significant attention in the last few years. Recently, convolutional neural networks have achieved great success in image dehazing. However, it is still difficult for these increasingly complex models to recover accurate details from the hazy image. In this paper, we pay attention to the feature extraction and utilization of the input image itself. To achieve this, we propose a Multi-scale Topological Network (MSTN) to fully explore the features at different scales. Meanwhile, we design a Multi-scale Feature Fusion Module (MFFM) and an Adaptive Feature Selection Module (AFSM) to achieve the selection and fusion of features at different scales, so as to achieve progressive image dehazing. This topological network provides a large number of search paths that enable the network to extract abundant image features as well as strong fault tolerance and robustness. In addition, ASFM and MFFM can adaptively select important features and ignore interference information when fusing different scale representations. Extensive experiments are conducted to demonstrate the superiority of our method compared with state-of-the-art methods.

show abstract

“…Real-world Dataset. We further evaluate our performance on three small-scale real-word datasets: DENSE-HAZE [1], NH-HAZE [3,2]…”

Section: Datasetsmentioning

confidence: 99%

DW-GAN: A Discrete Wavelet Transform GAN for NonHomogeneous Dehazing

Fu¹,

Huan²,

Yu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Hazy images are often subject to color distortion, blurring, and other visible quality degradation. Some existing CNN-based methods have great performance on removing homogeneous haze, but they are not robust in nonhomogeneous case. The reasons are mainly in two folds. Firstly, due to the complicated haze distribution, texture details are easy to be lost during the dehazing process. Secondly, since the training pairs are hard to be collected, training on limited data can easily lead to over-fitting problem. To tackle these two issues, we introduce a novel dehazing network using 2D discrete wavelet transform, namely DW-GAN. Specifically, we propose a two-branch network to deal with the aforementioned problems. By utilizing wavelet transform in DWT branch, our proposed method can retain more high-frequency knowledge in feature maps. In order to prevent over-fitting, ImageNet pre-trained Res2Net is adopted in the knowledge adaptation branch. Owing to the robust feature representations of ImageNet pre-training, the generalization ability of our network is improved dramatically. Finally, a patch-based discriminator is used to reduce artifacts of the restored images. Extensive experimental results demonstrate that the proposed method outperforms the state-of-the-arts quantitatively and qualitatively. The source code is available at https://github.com/ liuh127/DW-GAN-Dehazing.

show abstract

NTIRE 2020 Challenge on NonHomogeneous Dehazing

Cited by 73 publications

References 49 publications

Residual Spatial and Channel Attention Networks for Single Image Dehazing

Residual Spatial and Channel Attention Networks for Single Image Dehazing

Efficient and Accurate Multi-Scale Topological Network for Single Image Dehazing

DW-GAN: A Discrete Wavelet Transform GAN for NonHomogeneous Dehazing

Contact Info

Product

Resources

About