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

Wang, Yongzhen; Yan, Xuefeng; Guan, Donghai; Wei, Mingqiang; Chen, Yiping; Zhang, Xiao-Ping; Li, Jonathan

doi:10.1109/tits.2022.3170328

Cited by 38 publications

(22 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

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

Advancing Real-world Image Dehazing: A Comprehensive Dataset and Evaluation Metrics

Celona,

Piccoli

2024

Preprint

View full text Add to dashboard Cite

The majority of dehazing techniques in the literature have been designed to learn from supervised datasets, which typically comprise pairs of images, one with haze and one without haze, to facilitate the learning process. These datasets often contain synthesized hazy images, either created by leveraging the theoretical model of haze creation, or by exploiting professional haze generation machines. However, the lack of realism given by these generative processes has led to a limited capacity of dehazing techniques to effectively generalize on real-world images. Recently, a collection of real-world hazy image datasets has been collected, but with a reduced cardinality. This study aims to address the aforementioned issues and introduce the Unpaired Real-world Hazy Image Dataset (URHID). It is a large-scale benchmark dataset containing 13,329 real-world hazy images scraped from the Internet. In addition, a total of eight state-of-the-art dehazing methods were chosen to assess the performance of URHID. Given the lack of no-reference measures in the existing literature for evaluating the quality of unpaired dehazed images, this study aims to address this gap by proposing the Multi-Aspect Dehazed Image Quality Assessment (MADIQA) dataset. A collection of dehazed images annotated in terms of multiple quality-related aspects as well as overall quality. Furthermore, we develop multiple No-Reference Dehazed Image Quality Assessment (NR-DIQA) metrics. The proposed URHID and MADIQA datasets, as well as the proposed DIQA metrics are publicly available for research purposes at: https://celuigi.github.io/arid.github.io/.

show abstract

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%

Advancing Real-world Image Dehazing: A Comprehensive Dataset and Evaluation Metrics

Celona,

Piccoli

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…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%

TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learning

Wang

Yan

Zhang

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

Adverse weather conditions such as haze, rain, and snow often impair the quality of captured images, causing detection networks trained on normal images to generalize poorly in these scenarios. In this paper, we raise an intriguing question -if the combination of image restoration and object detection, can boost the performance of cutting-edge detectors in adverse weather conditions. To answer it, we propose an effective yet unified detection paradigm that bridges these two subtasks together via dynamic enhancement learning to discern objects in adverse weather conditions, called TogetherNet. Different from existing efforts that intuitively apply image dehazing/deraining as a pre-processing step, TogetherNet considers a multi-task joint learning problem. Following the joint learning scheme, clean features produced by the restoration network can be shared to learn better object detection in the detection network, thus helping TogetherNet enhance the detection capacity in adverse weather conditions. Besides the joint learning architecture, we design a new Dynamic Transformer Feature Enhancement module to improve the feature extraction and representation capabilities of TogetherNet. Extensive experiments on both synthetic and real-world datasets demonstrate that our TogetherNet outperforms the state-of-the-art detection approaches by a large margin both quantitatively and qualitatively. Source code is available at https://github.com/yz-wang/TogetherNet.

show abstract

“…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%

Retinex decomposition and fusion dehazing network

et al. 2023

View full text Add to dashboard Cite

Image dehazing has been widely used in vision-based fields, such as detection, segmentation, traffic monitoring, and automated vehicle system. However, most of the existing endto-end dehazing networks are fully data driven without physical constraints or prior information guidance, leading to difficulties in exploring latent structures and statistical characteristics of hazy images. We propose a novel Retinex decomposition-fusion dehazing network consisting of a dual-branch decomposition module and a fusion optimization module. Different from existing solutions, we decompose the clear images in the commonly used RESIDE dataset based on Retinex theory to construct the clear illumination map and reflection map datasets to drive the network training, equivalently imposing reasonable constraints on the network and achieving impressive dehazing performances. The dual-branch decomposition module is developed to estimate the illumination map and the reflection map, respectively. The illumination map mainly contains the global features of the image, whereas the reflection map reflects the inherent color properties of the image and contains rich details, with which we explore the latent structures and statistical characteristics of hazy images. In addition, the dual-branch structure avoids the error accumulation and information cancellation existing in current methods. Subsequently, the estimated illumination map and reflection map are fused and refined via the fusion optimization module to access the dehazed image. Experiments show that the proposed network has better generalization and visual effects than existing fully data-driven methods and can be applied successfully to real-world scenarios.

show abstract

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

Cited by 38 publications

References 56 publications

Advancing Real-world Image Dehazing: A Comprehensive Dataset and Evaluation Metrics

Advancing Real-world Image Dehazing: A Comprehensive Dataset and Evaluation Metrics

TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learning

Retinex decomposition and fusion dehazing network

Contact Info

Product

Resources

About