Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- ArticleAugust 2024
Uncertainty-Driven Multi-scale Feature Fusion Network for Real-Time Image Deraining
Advanced Intelligent Computing Technology and ApplicationsPages 74–85https://doi.org/10.1007/978-981-97-5591-2_7AbstractVisual-based measurement systems are frequently affected by rainy weather due to the degradation caused by rain streaks in captured images, and existing imaging devices struggle to address this issue in real-time. While most efforts leverage deep ...
- research-articleMay 2024
Feature decoupling and reorganization network for single image deraining
AbstractSingle image deraining has become an important preprocessing task in the multimedia area, improving the performance of subsequent high-level computer vision tasks in rainy weather significantly. Previous efforts to restore rain-damaged images have ...
- research-articleMay 2024
CTFCD: Channel transformer based on full convolutional decoder for single image deraining
Journal of Visual Communication and Image Representation (JVCIR), Volume 98, Issue Chttps://doi.org/10.1016/j.jvcir.2023.103992AbstractAlthough convolutional neural network and visual transformer have been successfully applied in various field of computer vision, there is little work combining them to construct an efficient network model to solve image deraining tasks. ...
- research-articleMarch 2024
Progressive network based on detail scaling and texture extraction: A more general framework for image deraining
AbstractMany feature extraction components have been proposed for image deraining tasks, aiming to improve feature learning. However, few models have addressed the integration of multi-scale features from derain images. The fusion of multiple features at ...
Highlights- Introduce detail scaling module to extract generalized features from rainfall image.
- Improved Transform block was introduced to enhance the model’s generalized ability.
- Scale-mixing strategy is proposed for capturing more multi-...
- research-articleMarch 2024
A novel dual-stage progressive enhancement network for single image deraining
Engineering Applications of Artificial Intelligence (EAAI), Volume 128, Issue Chttps://doi.org/10.1016/j.engappai.2023.107411AbstractThe dense rain accumulation in heavy rain can significantly wash out images and thus destroy the background details of images. Although existing deep rain removal models lead to improved performance for heavy rain removal, we find that most of ...
-
- research-articleFebruary 2024
Progressive dense feature fusion network for single image deraining
Pattern Recognition Letters (PTRL), Volume 176, Issue CPages 209–214https://doi.org/10.1016/j.patrec.2023.11.003AbstractDeep Learning (DL) has achieved significant progress in single image deraining methods. Most of current DL methods, however, are still weak in image detail recovery and feature inherent correlation learning. In this work, we explore the detail ...
Highlights- PFFM can excavate inherent features correlations and intensify the details feature.
- Detail perceptual loss is used to better measure the details difference.
- Contextual loss on target regions can recover the details of objects.
- ...
- ArticleDecember 2023
New Insights on the Generation of Rain Streaks: Generating-Removing United Unpaired Image Deraining Network
AbstractMost existing deraining methods use synthetic rainy images to train models. They focus on extracting the features to establish mapping models from rainy images to clean background images, while ignoring the domain gap between synthetic and real ...
- research-articleSeptember 2023
DeTformer: A Novel Efficient Transformer Framework for Image Deraining
Circuits, Systems, and Signal Processing (CSSP), Volume 43, Issue 2Pages 1030–1052https://doi.org/10.1007/s00034-023-02499-9AbstractCaptured rainy images severely degrade outdoor vision systems performance, such as semi-autonomous or autonomous driving systems and video surveillance systems. Consequently, removing heavy and complex rain streaks, i.e. undesirable rainy ...
- research-articleAugust 2023
Multi-aggregation network based on non-separable lifting wavelet for single image deraining
Multimedia Systems (MUME), Volume 29, Issue 6Pages 3669–3684https://doi.org/10.1007/s00530-023-01156-0AbstractRecently, many methods have utilized Haar wavelet to extract frequency-domain information for image deraining. However, Haar wavelet and other tensor product wavelets only capture high frequencies in horizontal, vertical, and diagonal directions, ...
- research-articleMay 2023
Local and global knowledge distillation with direction-enhanced contrastive learning for single-image deraining
AbstractSingle image deraining (SID) is a challenging problem since the rainy images contain a variety of backgrounds with rain streaks of different directions and densities. Though previous convolutional neural network based methods for SID have shown ...
- research-articleMay 2023
Single image deraining using modified bilateral recurrent network (modified_BRN)
Multimedia Tools and Applications (MTAA), Volume 83, Issue 2Pages 3373–3396https://doi.org/10.1007/s11042-023-15276-2AbstractThe process of reinstating a clean background to an image that has been destroyed by multiple rain streaks and rain built up is called Image Deraining. We propose a single recurrent network first that begins by iteratively unfolding one shallow-...
- research-articleMay 2023
Cascaded transformer U-net for image restoration
Highlights- A cascaded multi-stage framework is designed based on the transformer for image restoration.
Image restoration is one of the most important computer vision tasks, aiming at recovering high-quality images from degraded or low-quality observations. The restoration methods based on convolutional neural networks (CNNs) have ...
- research-articleFebruary 2023
Single image deraining using multi-scales context information and attention network
Journal of Visual Communication and Image Representation (JVCIR), Volume 90, Issue Chttps://doi.org/10.1016/j.jvcir.2022.103695Highlights- We proposed a novel CNN-based framework for image deraining.
- We designed a ...
The existing deraining methods based on convolutional neural networks (CNNs) have made great success, but some remaining rain streaks can degrade images drastically. In this work, we proposed an end-to-end multi-scale context ...
- ArticleMarch 2023
Multi-scale and Multi-stage Deraining Network with Fourier Space Loss
AbstractThe goal of rain streak removal is to recover the rain-free background scenes of an image degraded by rain streaks. Most current deep convolutional neural networks methods have achieved dramatic performance. However, these methods still cannot ...
- research-articleJanuary 2023
Cross-domain collaborative learning for single image deraining
Expert Systems with Applications: An International Journal (EXWA), Volume 211, Issue Chttps://doi.org/10.1016/j.eswa.2022.118611Highlights- We propose a cross-domain collaborative learning framework for image deraining.
- A cross-domain pseudo label generation method is presented.
- A Multi-Scale Attention Residual Block for improving the representation ability.
- The ...
Deep Convolutional Neural Networks (DCNN) have achieved outstanding performance in image deraining tasks. However, current most methods regard rain streak removal as a one-to-one problem, and intra domain shift of different synthetic datasets is ...
- research-articleDecember 2022
UnfairGAN: An enhanced generative adversarial network for raindrop removal from a single image
Expert Systems with Applications: An International Journal (EXWA), Volume 210, Issue Chttps://doi.org/10.1016/j.eswa.2022.118232AbstractImage deraining is a new challenging problem in real-world applications, such as autonomous vehicles. In a bad weather condition of heavy rainfall, raindrops, mainly hitting glasses or windshields, can significantly reduce observation ...
Graphical abstractDisplay Omitted
Highlights- Developing an advanced loss function that can improve the instabilities of GAN.
- research-articleDecember 2022
HDRD-Net: High-resolution detail-recovering image deraining network
Multimedia Tools and Applications (MTAA), Volume 81, Issue 29Pages 42889–42906https://doi.org/10.1007/s11042-022-13489-5AbstractImage deraining aims to restore the clean scenes of rainy images, which facilitates a number of outdoor vision systems, such as autonomous driving, unmanned aerial vehicles and surveillance systems. This paper proposes a high-resolution detail-...
- ArticleApril 2023
Graph-Based Contextual Attention Network for Single Image Deraining
AbstractRain streaks degrade the images and badly affect the outdoor vison tasks, and deep learning based single image deraining approach has witnessed the continuously growing and achieved great success. However, traditional convolution operation which ...
- ArticleOctober 2022
Learning Contextual Embedding Deep Networks for Accurate and Efficient Image Deraining
AbstractThe existing state-of-the-art deraining methods rely on a bulky network structure to accurately capture rain streaks, resulting in prohibitive memory consumption and computation cost. In addition, most of them destroy background details along with ...
- research-articleJune 2022
Single image deraining with dual U-Net generative adversarial network
Multidimensional Systems and Signal Processing (MULT), Volume 33, Issue 2Pages 485–499https://doi.org/10.1007/s11045-021-00806-8AbstractMost of the existing deraining methods cannot preserve the details of the image while removing the rain streaks. To solve this problem, we propose a single image de-raining method with dual U-Net generative adversarial network (DU-GAN). By using ...