2022
DOI: 10.1109/tits.2022.3170328
|View full text |Cite
|
Sign up to set email alerts
|

Cycle-SNSPGAN: Towards Real-World Image Dehazing via Cycle Spectral Normalized Soft Likelihood Estimation Patch GAN

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
22
0

Year Published

2022
2022
2025
2025

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 51 publications
(22 citation statements)
references
References 56 publications
0
22
0
Order By: Relevance
“…Dehazing methods can be categorized as supervised [29,45], semi-supervised [9,22,28], and unsupervised [27,44,47], depending on whether they necessitate for training a collection of hazy and haze-free image pairs, a combination of both paired and unpaired images, or solely unpaired hazy images.…”
Section: Semi-/un-supervised Dehazing Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…Dehazing methods can be categorized as supervised [29,45], semi-supervised [9,22,28], and unsupervised [27,44,47], depending on whether they necessitate for training a collection of hazy and haze-free image pairs, a combination of both paired and unpaired images, or solely unpaired hazy images.…”
Section: Semi-/un-supervised Dehazing Methodsmentioning
confidence: 99%
“…To overcome this limitation, many researchers use unconstrained imageto-image regression techniques. In particular, through deep learning, it is possible to design data-driven methods that are capable of reconstruct the source image faithfully [5,13,44].…”
Section: Real-world Hazy Imagementioning
confidence: 99%
“…Compared with general object detection, few research efforts have been explored on object detection in adverse weather conditions. Early methods mainly focused on pre‐processing the degraded images by existing restoration algorithms such as image dehazing [HST11, QWB*20, WYG*22, SZB*22] or image deraining [LQS*19, RLHS20a, DWW*20], and then sending the processed images to the subsequent detection network for object detection. Although employing image restoration approaches as a preprocessing step can improve the overall quality of degraded images, these images may not definitely benefit the detection performance.…”
Section: Related Workmentioning
confidence: 99%
“…Recently, unsupervised dehazing methods based on generative adversarial networks (GANs) have been developed. [12][13][14][15] However, the dehazing networks based on GANs have a high computational complexity and long running time, making them not suitable for real-world application scenarios. Supervised learning methods include scattering model-based deep networks (DehazeNet, 16 AOD-Net, 17 and DCDPN 18 ) and end-to-end deep networks [gated fusion network (GFN), 19 enhanced pix2pix dehazing network (EPDN), 20 gated context aggregation network (GCANet), 21 and Y-Net 22 ].…”
Section: Introductionmentioning
confidence: 99%
“…The existing learning-based methods can be divided into unsupervised learning methods and supervised learning methods. Recently, unsupervised dehazing methods based on generative adversarial networks (GANs) have been developed 12 15 However, the dehazing networks based on GANs have a high computational complexity and long running time, making them not suitable for real-world application scenarios.…”
Section: Introductionmentioning
confidence: 99%