Multi-Scale Progressive Fusion Network for Single Image Deraining

Jiang, Kui; Wang, Zhongyuan; Yi, Peng; Chen, Chen; Huang, Baojin; Luo, Yi; Ma, Jiayi; Jiang, Junjun

doi:10.1109/cvpr42600.2020.00837

Cited by 542 publications

(323 citation statements)

References 35 publications

Supporting

Mentioning

321

Contrasting

Unclassified

Order By: Relevance

“…Jiang et al [45] proposed to decompose rain streaks into multiple rain layers and individually estimate each of them along the network stages to cope with the deraining problem. Jiang et al [46] applied the multi-scale collaborative representation for rain streaks from the perspective of input image scales and hierarchical deep features in a unified framework to remove rain streaks.…”

Section: B Single-image Based Methodsmentioning

confidence: 99%

Enhanced Attentive Generative Adversarial Network for Single-Image Deraining

et al. 2021

View full text Add to dashboard Cite

The problem of image rain removal has drawn widespread attention as the blurry images caused by rain streaks can degrade the performance of many computer vision tasks. Although exiting deep learning-based methods outperform most traditional methods, there are still unresolved issues in terms of performance. In this paper, we propose a novel enhanced attentive generative adversarial network named EAGAN to effectively remove the rain streaks and restore the image structural details at the same time. As rain streaks have different sizes and shapes, EAGAN utilizes a multiscale aggregation attention module (MAAM) to produce an attention map to guide the subsequent network to put conscious attention to rain regions. A symmetrical autoencoder with long-range skip-connections, squeeze-and-excitation (SE) modules, and non-local operation is further utilized to enhance the representation of the network. Finally, spectral normalization and a relativistic generative adversarial network (GAN) are further applied to improve the training stability and deraining performance. Both qualitative and quantitative validations on synthetic and real-world datasets demonstrate that the proposed approach can achieve a competitive performance in comparison with the state-of-the-art methods.INDEX TERMS Image deraining, attentive module, relativistic GAN.

show abstract

Section: B Single-image Based Methodsmentioning

confidence: 99%

Enhanced Attentive Generative Adversarial Network for Single-Image Deraining

et al. 2021

View full text Add to dashboard Cite

show abstract

“…This motivates us to incorporate the raindrop removal method as a form of preprocessing into high-level applications. In this paper, following [ 45 ], we introduce pre-trained models of PSPNet [ 46 ] (for semantic segmentation) and Faster R-CNN [ 47 ] (for object detection) trained on the Cityscapes dataset to perform an evaluation of segmentation and detection precision, respectively. Table 5 tabulates the accuracy of segmentation under different deraining methods on the RaindropCityscapes dataset, in terms of the mean Intersection of Union (mIoU) and mean Accuracy of each class (mAcc).…”

Section: Methodsmentioning

confidence: 99%

Multi-Scale Shape Adaptive Network for Raindrop Detection and Removal from a Single Image

Luo

et al. 2020

Sensors

View full text Add to dashboard Cite

Removing raindrops from a single image is a challenging problem due to the complex changes in shape, scale, and transparency among raindrops. Previous explorations have mainly been limited in two ways. First, publicly available raindrop image datasets have limited capacity in terms of modeling raindrop characteristics (e.g., raindrop collision and fusion) in real-world scenes. Second, recent deraining methods tend to apply shape-invariant filters to cope with diverse rainy images and fail to remove raindrops that are especially varied in shape and scale. In this paper, we address these raindrop removal problems from two perspectives. First, we establish a large-scale dataset named RaindropCityscapes, which includes 11,583 pairs of raindrop and raindrop-free images, covering a wide variety of raindrops and background scenarios. Second, a two-branch Multi-scale Shape Adaptive Network (MSANet) is proposed to detect and remove diverse raindrops, effectively filtering the occluded raindrop regions and keeping the clean background well-preserved. Extensive experiments on synthetic and real-world datasets demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art raindrop removal methods. Moreover, the extension of our method towards the rainy image segmentation and detection tasks validates the practicality of the proposed method in outdoor applications.

show abstract

“…In particular, L MAE is defined as e high-frequency detail information is easily destroyed in the process of image dehazing. To further improve the fidelity and authenticity of details, we propose an additional edge loss function [36] to limit the high-frequency components, for example, edge and texture. L Edge can be written as…”

Section: Journal Of Advanced Transportationmentioning

confidence: 99%

“…In addition, the Total Variation (TV) loss function [37] is exploited to suppress the pixel-jump problem, which can be given bywhere ∇ h and ∇ v represent the operators of the horizontal and vertical gradients, respectively. We refer interested readers to [35][36][37] for more details on calculations of MS-SSIM, edge loss, and TV. To sum up, the total loss function can be written as follows:…”

Section: Journal Of Advanced Transportationmentioning

confidence: 99%

CNN-Enabled Visibility Enhancement Framework for Vessel Detection under Haze Environment

Guo

Liang

2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

Maritime images captured under haze environment often have a terrible visual effect, making it easy to overlook important information. To avoid the failure of vessel detection caused by fog, it is necessary to preprocess the collected hazy images for recovering vital information. In this paper, a novel CNN-enabled visibility dehazing framework is proposed, consisting of two subnetworks, that is, Coarse Feature Extraction Module (C-FEM) and Fine Feature Fusion Module (F-FFM). Specifically, C-FEM is a multiscale haze feature extraction network, which can learn information from three scales. Correspondingly, F-FFM is an improved encoder-decoder network to fuse multiscale information obtained by C-FEM and enhance the visual effect of the final output. Meanwhile, a hybrid loss function is designed for monitoring the multiscale output of C-FEM and the final result of F-FFM simultaneously. It is worth mentioning that massive maritime images are considered the training dataset to further adapt the vessel detection task under haze environment. Comprehensive experiments on synthetic and realistic images have verified the superior effectiveness and robustness of our CNN-enabled visibility dehazing framework compared to several state-of-the-art methods. Our method preprocesses images before vessel detection to demonstrate our framework has the capacity of promoting maritime video surveillance.

show abstract

Multi-Scale Progressive Fusion Network for Single Image Deraining

Cited by 542 publications

References 35 publications

Enhanced Attentive Generative Adversarial Network for Single-Image Deraining

Enhanced Attentive Generative Adversarial Network for Single-Image Deraining

Multi-Scale Shape Adaptive Network for Raindrop Detection and Removal from a Single Image

CNN-Enabled Visibility Enhancement Framework for Vessel Detection under Haze Environment

Contact Info

Product

Resources

About