用于单一图像去粒度的递归注意力协作网络

IF 1.5 Q3 AUTOMATION & CONTROL SYSTEMS
Zhitong Li, Xiaodong Li, Zhaozhe Gong, Zhensheng Yu
{"title":"用于单一图像去粒度的递归注意力协作网络","authors":"Zhitong Li,&nbsp;Xiaodong Li,&nbsp;Zhaozhe Gong,&nbsp;Zhensheng Yu","doi":"10.1049/csy2.12115","DOIUrl":null,"url":null,"abstract":"<p>Single-image rain removal is an important problem in the field of computer vision aimed at recovering clean images from rainy images. In recent years, data-driven convolutional neural network (CNN)-based rain removal methods have achieved significant results, but most of them cannot fully focus on the contextual information in rain-containing images, which leads to the failure of recovering some of the background details of the images that have been corrupted due to the aggregation of rain streaks. With the success of Transformer-based models in the field of computer vision, global features can be easily acquired to better help recover details in the background of an image. However, Transformer-based models often require a large number of parameters during the training process, which makes the training process very difficult and makes it difficult to apply them to specific devices for execution in reality. The authors propose a Recursive Attention Collaboration Network, which consists of a recursive Swin-transformer block (STB) and a CNN-based feature fusion block. The authors designed the Recursively Integrate Transformer Block (RITB), which consists of several STBs recursively connected, that can effectively reduce the number of parameters of the model. The final part of the module can integrate the local information from the STBs. The authors also design the Feature Enhancement Block, which can better recover the details of the background information corrupted by rain streaks of different density shapes through the features passed from the RITB. Experiments show that the proposed network has an effective rain removal effect on both synthetic and real datasets and has fewer model parameters than other mainstream methods.</p>","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"6 2","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/csy2.12115","citationCount":"0","resultStr":"{\"title\":\"Recursive attention collaboration network for single image de-raining\",\"authors\":\"Zhitong Li,&nbsp;Xiaodong Li,&nbsp;Zhaozhe Gong,&nbsp;Zhensheng Yu\",\"doi\":\"10.1049/csy2.12115\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Single-image rain removal is an important problem in the field of computer vision aimed at recovering clean images from rainy images. In recent years, data-driven convolutional neural network (CNN)-based rain removal methods have achieved significant results, but most of them cannot fully focus on the contextual information in rain-containing images, which leads to the failure of recovering some of the background details of the images that have been corrupted due to the aggregation of rain streaks. With the success of Transformer-based models in the field of computer vision, global features can be easily acquired to better help recover details in the background of an image. However, Transformer-based models often require a large number of parameters during the training process, which makes the training process very difficult and makes it difficult to apply them to specific devices for execution in reality. The authors propose a Recursive Attention Collaboration Network, which consists of a recursive Swin-transformer block (STB) and a CNN-based feature fusion block. The authors designed the Recursively Integrate Transformer Block (RITB), which consists of several STBs recursively connected, that can effectively reduce the number of parameters of the model. The final part of the module can integrate the local information from the STBs. The authors also design the Feature Enhancement Block, which can better recover the details of the background information corrupted by rain streaks of different density shapes through the features passed from the RITB. Experiments show that the proposed network has an effective rain removal effect on both synthetic and real datasets and has fewer model parameters than other mainstream methods.</p>\",\"PeriodicalId\":34110,\"journal\":{\"name\":\"IET Cybersystems and Robotics\",\"volume\":\"6 2\",\"pages\":\"\"},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2024-04-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1049/csy2.12115\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IET Cybersystems and Robotics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1049/csy2.12115\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"AUTOMATION & CONTROL SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IET Cybersystems and Robotics","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/csy2.12115","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

单图像雨点去除是计算机视觉领域的一个重要问题,旨在从雨点图像中恢复干净图像。近年来,基于数据驱动的卷积神经网络(CNN)的雨点去除方法取得了显著成效,但大多数方法不能完全关注含雨图像中的上下文信息,导致无法恢复因雨点条纹聚集而损坏的图像的部分背景细节。随着基于变换器的模型在计算机视觉领域取得成功,全局特征可以很容易地获取,从而更好地帮助恢复图像背景中的细节。然而,基于变换器的模型在训练过程中往往需要大量的参数,这给训练过程带来了很大的困难,也很难将其应用到特定的设备上在现实中执行。作者提出了一种递归注意力协作网络,它由一个递归斯温变换器模块(STB)和一个基于 CNN 的特征融合模块组成。作者设计的递归整合变换器模块(RITB)由多个递归连接的 STB 组成,可以有效减少模型的参数数量。模块的最后一部分可以整合来自 STB 的本地信息。作者还设计了特征增强块,通过 RITB 传递的特征,可以更好地恢复被不同密度形状的雨条纹破坏的背景信息细节。实验表明,所提出的网络在合成数据集和真实数据集上都具有有效的雨水去除效果,而且与其他主流方法相比,其模型参数更少。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Recursive attention collaboration network for single image de-raining

Recursive attention collaboration network for single image de-raining

Single-image rain removal is an important problem in the field of computer vision aimed at recovering clean images from rainy images. In recent years, data-driven convolutional neural network (CNN)-based rain removal methods have achieved significant results, but most of them cannot fully focus on the contextual information in rain-containing images, which leads to the failure of recovering some of the background details of the images that have been corrupted due to the aggregation of rain streaks. With the success of Transformer-based models in the field of computer vision, global features can be easily acquired to better help recover details in the background of an image. However, Transformer-based models often require a large number of parameters during the training process, which makes the training process very difficult and makes it difficult to apply them to specific devices for execution in reality. The authors propose a Recursive Attention Collaboration Network, which consists of a recursive Swin-transformer block (STB) and a CNN-based feature fusion block. The authors designed the Recursively Integrate Transformer Block (RITB), which consists of several STBs recursively connected, that can effectively reduce the number of parameters of the model. The final part of the module can integrate the local information from the STBs. The authors also design the Feature Enhancement Block, which can better recover the details of the background information corrupted by rain streaks of different density shapes through the features passed from the RITB. Experiments show that the proposed network has an effective rain removal effect on both synthetic and real datasets and has fewer model parameters than other mainstream methods.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
IET Cybersystems and Robotics
IET Cybersystems and Robotics Computer Science-Information Systems
CiteScore
3.70
自引率
0.00%
发文量
31
审稿时长
34 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信