FastDerainNet: A Deep Learning Algorithm for Single Image Deraining

Wang, Xiuwen; Li, Zhiwei; Shan, Hongtao; Tian, Zhiyuan; Ren, Yuanhong; Zhou, Wuneng

doi:10.1109/access.2020.3008324

Cited by 13 publications

(5 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jiang et al [27] proposed a multi-scale progressive fusion network, which captured rain streaks by fusing features in a multi-scale collaborative way and circular calculations and used the captured rain streaks to restore the background. Wang et al [28] proposed a deep residual learning model based on FastDerainnet. This model first used a low-pass filter and high-pass filter to remove rain streaks preliminarily, then used the residual structure on the high-frequency component to learn the residual features of rain streaks, and at last used high-frequency components and low-frequency components to calculate rainless background images.…”

Section: B Single-image Deraining Methodsmentioning

confidence: 99%

ETDNet: An Efficient Transformer Deraining Model

Qin

Yan²,

Wang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Rainy days usually degrade the visual effect of images and videos. At present, most deraining models for single images adopt gradual optimization or elimination to remove rain streaks, but actually with relatively low efficiency in real tasks. An efficient one-stage deraining model, Efficient Transformer Derain Network (ETDNet), is proposed to remove rain streaks in single images efficiently. A new Transformer architecture is designed to provide rich multiple scales and context information, making the model extract features in a coarse-to-fine way. Multiple expansion filters with different expansion rates are embedded to predict the suitable kernel for each pixel of the rainy image in a multi-scale way. A multi-scale Loss Function is introduced to restore features with high-fidelity and detail textures. Experiments on Rain100L, Rain100H, and SPA datasets show that compared with other models, the proposed ETDNet reaches the highest PSNR and SSIM values at the fastest speed.

show abstract

Section: B Single-image Deraining Methodsmentioning

confidence: 99%

ETDNet: An Efficient Transformer Deraining Model

Qin

Yan²,

Wang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Still, the failure in considering the texture features degrades the performance of the model. www.ijacsa.thesai.org Wang et al [27] designed a deep learning based image deraining model, wherein the shared source residual module was incorporated in the conventional deep convolutional neural network for making the skip connection to solve the vanishing gradient issues. The computational overhead evaluated by the designed model was minimal with enhanced outcome.…”

Section: Related Workmentioning

confidence: 99%

Rain Streaks Removal in Images using Extended Generative Adversarial-based Deraining Framework

Gogulamudi¹,

Mahalakshmi²,

Sreeram³

2023

IJACSA

View full text Add to dashboard Cite

The visual quality of photographs and videos can be negatively impacted by various weather conditions, such as snow, haze, or rain, affecting the quality of the images and videos. Such impacts may greatly affect outdoor vision systems that rely on image/video data. It has recently drawn a lot of interest to remove rain streaks from a single image. Several deep learning-based methods have been introduced to address the issue of removing rain streaks from a single image. Still, the efficiency of rain streak removal with enhanced quality is challenging. Hence, a novel deep-learning method is introduced for rain streak removal. The proposed Extended Generative Adversarial based De-raining (Ex_GADerain) is the enhanced version of a traditional Generative adversarial network (GAN). The proposed Ex_GADerain introduced a Self-Attention based Convolutional Capsule Bidirectional Network (SA-CCapBiNet) based generator for enhancing the rain streaks removal process. Also, the loss function estimation using the adversarial loss and the mean absolute error loss minimizes the information loss during training. The minimal information loss enhances the generalization capability of Ex_GADerain, and hence the enhanced performance is acquired. The quality assessment of a derained image based on various assessment measures like SSIM, PSNR, RMSE, and DSSIM improved performance compared to the conventional rain streak removal methods. The maximal SSIM and PSNR acquired by the Ex_GADerain are 0.9923 and 26.7052, respectively. The minimal RMSE and DSSIM acquired by the Ex_GADerain are 0.9367 and 0.0051, respectively.

show abstract

“…In the deep learning era, learning-based methods [4], [5], [15], [34], [35], [37], [41], [43] have shown dramatic improvements from labeled datasets. Fu et al [4] applied a low pass filter to decompose the rain image into two components, the base, and the detail parts, then utilized a ResNet for training their network to predict the detail component.…”

Section: B Single Image Derainingmentioning

confidence: 99%

Exploiting Global and Local Attentions for Heavy Rain Removal on Single Images

Vu¹,

Gonzalez²,

Kim³

2021

Preprint

View full text Add to dashboard Cite

Heavy rain removal from a single image is the task of simultaneously eliminating rain streaks and fog, which can dramatically degrade the quality of captured images. Most existing rain removal methods do not generalize well for the heavy rain case. In this work, we propose a novel network architecture consisting of three sub-networks to remove heavy rain from a single image without estimating rain streaks and fog separately. The first sub-net, a U-net-based architecture that incorporates our Spatial Channel Attention (SCA) blocks, extracts global features that provide sufficient contextual information needed to remove atmospheric distortions caused by rain and fog. The second sub-net learns the additive residues information, which is useful in removing rain streak artifacts via our proposed Residual Inception Modules (RIM). The third sub-net, the multiplicative sub-net, adopts our Channel-attentive Inception Modules (CIM) and learns the essential brighter local features which are not effectively extracted in the SCA and additive sub-nets by modulating the local pixel intensities in the derained images. Our three clean image results are then combined via an attentive blending block to generate the final clean image. Our method with SCA, RIM, and CIM significantly outperforms the previous state-of-the-art single-image deraining methods on the synthetic datasets, shows considerably cleaner and sharper derained estimates on the real image datasets. We present extensive experiments and ablation studies supporting each of our method's contributions on both synthetic and real image datasets.INDEX TERMS Heavy rain removal, Single image deraining, Image restoration, Deep learning.

show abstract

FastDerainNet: A Deep Learning Algorithm for Single Image Deraining

Cited by 13 publications

References 39 publications

ETDNet: An Efficient Transformer Deraining Model

ETDNet: An Efficient Transformer Deraining Model

Rain Streaks Removal in Images using Extended Generative Adversarial-based Deraining Framework

Exploiting Global and Local Attentions for Heavy Rain Removal on Single Images

Contact Info

Product

Resources

About