Multi-Medium Image Enhancement With Attentive Deformable Transformers

IF 5.3 3区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Ashutosh Kulkarni;Shruti S. Phutke;Santosh Kumar Vipparthi;Subrahmanyam Murala
{"title":"Multi-Medium Image Enhancement With Attentive Deformable Transformers","authors":"Ashutosh Kulkarni;Shruti S. Phutke;Santosh Kumar Vipparthi;Subrahmanyam Murala","doi":"10.1109/TETCI.2024.3451550","DOIUrl":null,"url":null,"abstract":"Visibility challenges such as atmospheric haze, water turbidity, etc. are imposed while capturing images in various mediums like aerial, outdoor, underwater, etc. Such reduction in visibility affects the functioning of high-level computer vision applications like object detection, semantic segmentation, military surveillance, earthquake assessment, etc. The existing methods either rely on incorporating additional prior information during the training process or yield less than optimal results when analysed on images with varying levels of degradation, reason being the absence of both local and global dependencies within the extracted features. This paper presents a generalized transformer based architecture for aerial, outdoor and underwater image enhancement. We propose a novel space aware deformable convolution based multi-head self attention containing spatially attentive offset extraction. Here, the deformable multi-head attention is introduced to reconstruct fine level texture in the restored image. Additionally, we introduce a spatially attentive offset extractor within the deformable convolution to prioritize relevant contextual information. Further, we propose an edge enhancing feature fusion block for restoring the edge details in the image along with learning enriched features from multi-stream information. Finally, we propose a global context aware channel attentive feature propagator having a dual functionality of global information extraction and provision of channel attention. Comprehensive experimentation conducted on both synthetic and real-world datasets, along with thorough ablation study, showcases that the proposed approach performs optimally when compared with the existing methods on aerial, outdoor, and underwater image enhancement.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"9 2","pages":"1659-1672"},"PeriodicalIF":5.3000,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Emerging Topics in Computational Intelligence","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10666800/","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Visibility challenges such as atmospheric haze, water turbidity, etc. are imposed while capturing images in various mediums like aerial, outdoor, underwater, etc. Such reduction in visibility affects the functioning of high-level computer vision applications like object detection, semantic segmentation, military surveillance, earthquake assessment, etc. The existing methods either rely on incorporating additional prior information during the training process or yield less than optimal results when analysed on images with varying levels of degradation, reason being the absence of both local and global dependencies within the extracted features. This paper presents a generalized transformer based architecture for aerial, outdoor and underwater image enhancement. We propose a novel space aware deformable convolution based multi-head self attention containing spatially attentive offset extraction. Here, the deformable multi-head attention is introduced to reconstruct fine level texture in the restored image. Additionally, we introduce a spatially attentive offset extractor within the deformable convolution to prioritize relevant contextual information. Further, we propose an edge enhancing feature fusion block for restoring the edge details in the image along with learning enriched features from multi-stream information. Finally, we propose a global context aware channel attentive feature propagator having a dual functionality of global information extraction and provision of channel attention. Comprehensive experimentation conducted on both synthetic and real-world datasets, along with thorough ablation study, showcases that the proposed approach performs optimally when compared with the existing methods on aerial, outdoor, and underwater image enhancement.
多介质图像增强与细心变形变压器
在空中、室外、水下等各种媒介中拍摄图像时,会遇到大气雾霾、水浑浊等能见度挑战。这种可见性的降低影响了高级计算机视觉应用的功能,如物体检测、语义分割、军事监视、地震评估等。现有的方法要么依赖于在训练过程中加入额外的先验信息,要么在分析具有不同退化程度的图像时产生的结果不太理想,原因是提取的特征中缺乏局部和全局依赖关系。本文提出了一种基于广义变压器的空中、室外和水下图像增强体系结构。我们提出了一种新的基于空间感知变形卷积的多头自注意方法,该方法包含空间注意偏移提取。在此,引入可变形多头注意力来重建恢复图像中的精细层次纹理。此外,我们在可变形卷积中引入了空间关注偏移提取器,以优先考虑相关的上下文信息。此外,我们提出了一种边缘增强特征融合块,用于恢复图像中的边缘细节,并从多流信息中学习丰富的特征。最后,我们提出了一种具有全局信息提取和提供信道关注双重功能的全局上下文感知信道关注特征传播器。在合成和真实数据集上进行的综合实验以及彻底的消融研究表明,与现有的空中、室外和水下图像增强方法相比,所提出的方法具有最佳性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
10.30
自引率
7.50%
发文量
147
期刊介绍: The IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI) publishes original articles on emerging aspects of computational intelligence, including theory, applications, and surveys. TETCI is an electronics only publication. TETCI publishes six issues per year. Authors are encouraged to submit manuscripts in any emerging topic in computational intelligence, especially nature-inspired computing topics not covered by other IEEE Computational Intelligence Society journals. A few such illustrative examples are glial cell networks, computational neuroscience, Brain Computer Interface, ambient intelligence, non-fuzzy computing with words, artificial life, cultural learning, artificial endocrine networks, social reasoning, artificial hormone networks, computational intelligence for the IoT and Smart-X technologies.
×
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