A two‐stage method for single image de‐raining based on attention smoothed dilated network

Du, Shuangli; Fan, Hengrui; Zhao, Minghua; Zong, Haomai; Hu, Jing

doi:10.1049/ipr2.12504

Cited by 5 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning-based deraining networks have received much attention recently for their strong feature representation capabilities. Various deraining network models have emerged, among which the representative ones are: deraining according to rainwater density classification [9], rainwater removal by recycling network [10,11], and using GAN [12,13] or teacher-student [14] networks to remove rain streaks. The advantages and disadvantages of the two rain removal methods, traditional and deep networks, will be thoroughly discussed later.…”

Section: O(x) = B(x) + R(x)mentioning

confidence: 99%

“…The module focuses on the location of rain patterns while better recovering the background image with contextual information to minimize the loss of texture and detail in the background. And we use multi-stage progressive [10,28] deraining so that each stage is a guide to the next stage. Next, to address the problem of catastrophic forgetting in deep learning image deraining, this paper introduces the parameter importance guidance method PIGWM [29].…”

Section: O(x) = B(x) + R(x)mentioning

confidence: 99%

See 1 more Smart Citation

Continuous learning deraining network based on residual FFT convolution and contextual transformer module

Zhang

Peng

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Single image deraining work has attracted a lot of attention. So an effective single image deraining network model, RFCTNet, is designed. Specifically, the residual Fast Fourier Transform convolution module is used as a baseline for the deraining network. The advantage is its ability to capture both long and short‐term information interactions and to integrate high and low‐frequency background information for delivery. And a novel Transformer module, the Contextual Transformer module, is introduced. Contextual knowledge of the rain streaks neighbourhood is learned to improve the recovery of textures and information in the image background based on focusing on the rain pattern features. Because of the overlap between rain streaks, removing them in one stage is difficult, so a multi‐stage progressive rain removal method is used. Considering the catastrophic forgetting problem of deep learning, a continuous learning method, PIGWM, is adopted, which is c and enables the network model to memorize of the previous data set. Also, the rain removal method RFCTNet has been proven through extensive experiments to outperform other advanced methods' evaluation metrics on both synthetic and real datasets. The source code can be found on https://github.com/SUTwu/RFCTNet

show abstract

Section: O(x) = B(x) + R(x)mentioning

confidence: 99%

Section: O(x) = B(x) + R(x)mentioning

confidence: 99%

Continuous learning deraining network based on residual FFT convolution and contextual transformer module

Zhang

Peng

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…In other words, our proposed bilateral grid learning stage and joint feature refinement are necessary for image clarity. In addition, the two-stage deraining method SDN [49] is also used to compare with our method. To be fair, SDN was retrained by using the same training dataset.…”

Section: Ablation Study On Two-stagementioning

confidence: 99%

Two‐stage learning framework for single image deraining

Jiang

Chen

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Single image deraining methods have been extensively studied for its ability to remarkably improve the performance of computer vision tasks in rainy environments. However, most existing rain removal methods still have two major drawbacks which are hindering the technology development. First, the rain streaks are seriously coupled with the background information in a single rainy image, which leads to incorrect identification of rain streaks by many methods and further makes the loss of texture details in the rain removal results. Second, they spend excessive computational cost, which is not conducive to practical applications. To address these issues, a progressive separation network (PSN) is proposed by decomposing the rain removal task into two stages, the bilateral grid learning stage and the joint feature refinement stage, from a novel perspective. The bilateral grid learning stage is designed to expand the distance between the rain streaks and the background information while preserving the image edge details to guide the subsequent refinement. For the joint feature refinement stage, a dual‐path interaction module is constructed to dynamically and gradually decouple the rain streak content and the intermediate features of the clear image details. In addition, an activation‐free feature refinement block is designed to further improve the computational efficiency by removing or replacing the activation function without loss of accuracy. Extensive experiments on synthetic and real datasets show that PSN outperforms state‐of‐the‐art rain removal methods in terms of quantitative accuracy and subjective visual quality. Furthermore, competitive results are derived by extending PSN to the defogging task.

show abstract

A novel CNN framework for skin disease classification using adaptive percentage filter for image binarization and fast-marching inpainting method

et al. 2024

Multimed Tools Appl

View full text Add to dashboard Cite

A two‐stage method for single image de‐raining based on attention smoothed dilated network

Cited by 5 publications

References 32 publications

Continuous learning deraining network based on residual FFT convolution and contextual transformer module

Continuous learning deraining network based on residual FFT convolution and contextual transformer module

Two‐stage learning framework for single image deraining

A novel CNN framework for skin disease classification using adaptive percentage filter for image binarization and fast-marching inpainting method

Contact Info

Product

Resources

About