PMCN: Parallax-motion collaboration network for stereo video dehazing

IF 7.2 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Chang Wu , Gang He , Wanlin Zhao , Xinquan Lai , Yunsong Li
{"title":"PMCN: Parallax-motion collaboration network for stereo video dehazing","authors":"Chang Wu ,&nbsp;Gang He ,&nbsp;Wanlin Zhao ,&nbsp;Xinquan Lai ,&nbsp;Yunsong Li","doi":"10.1016/j.knosys.2024.112681","DOIUrl":null,"url":null,"abstract":"<div><div>Despite progress in learning-based stereo dehazing, few studies have focused on stereo video dehazing (SVD). Existing methods may fall short in the SVD task by not fully leveraging multi-domain information. To address this gap, we propose a parallax-motion collaboration network (PMCN) that integrates parallax and motion information for efficient stereo video fog removal. We delicately design a parallax-motion collaboration block (PMCB) as the critical component of PMCN. Firstly, to capture binocular parallax correspondences more efficiently, we introduce a window-based parallax attention mechanism (W-PAM) in the parallax interaction module (PIM) of PMCB. By horizontally splitting the whole frame into multiple windows and extracting parallax relationships within each window, memory usage and runtime can be reduced. Meanwhile, we further conduct horizontal feature modulation to handle cross-window disparity variations. Secondly, a motion alignment module (MAM) based on deformable convolution explores the temporal correlation in the feature space for an independent view. Finally, we propose a fog-adaptive refinement module (FARM) to refine the features after interaction and alignment. FARM incorporates fog prior information and guides the network in dynamically generating processing kernels for dehazing to adapt to different fog scenarios. Quantitative and qualitative results demonstrate that the proposed PMCN outperforms state-of-the-art methods on both synthetic and real-world datasets. In addition, our PMCN also benefits the accuracy improvement for high-level vision tasks in fog scenes, e.g., object detection and stereo matching.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":null,"pages":null},"PeriodicalIF":7.2000,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Knowledge-Based Systems","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0950705124013157","RegionNum":1,"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

Despite progress in learning-based stereo dehazing, few studies have focused on stereo video dehazing (SVD). Existing methods may fall short in the SVD task by not fully leveraging multi-domain information. To address this gap, we propose a parallax-motion collaboration network (PMCN) that integrates parallax and motion information for efficient stereo video fog removal. We delicately design a parallax-motion collaboration block (PMCB) as the critical component of PMCN. Firstly, to capture binocular parallax correspondences more efficiently, we introduce a window-based parallax attention mechanism (W-PAM) in the parallax interaction module (PIM) of PMCB. By horizontally splitting the whole frame into multiple windows and extracting parallax relationships within each window, memory usage and runtime can be reduced. Meanwhile, we further conduct horizontal feature modulation to handle cross-window disparity variations. Secondly, a motion alignment module (MAM) based on deformable convolution explores the temporal correlation in the feature space for an independent view. Finally, we propose a fog-adaptive refinement module (FARM) to refine the features after interaction and alignment. FARM incorporates fog prior information and guides the network in dynamically generating processing kernels for dehazing to adapt to different fog scenarios. Quantitative and qualitative results demonstrate that the proposed PMCN outperforms state-of-the-art methods on both synthetic and real-world datasets. In addition, our PMCN also benefits the accuracy improvement for high-level vision tasks in fog scenes, e.g., object detection and stereo matching.
PMCN:用于立体视频去毛刺的视差-运动协作网络
尽管在基于学习的立体去毛刺方面取得了进展,但很少有研究关注立体视频去毛刺(SVD)。现有的方法可能无法充分利用多域信息,因此在 SVD 任务中存在不足。为了弥补这一不足,我们提出了视差-运动协作网络(PMCN),该网络整合了视差和运动信息,可实现高效的立体视频去雾。我们精心设计了视差-运动协作块(PMCB),作为 PMCN 的关键组成部分。首先,为了更有效地捕捉双眼视差对应,我们在 PMCB 的视差交互模块(PIM)中引入了基于窗口的视差关注机制(W-PAM)。通过将整帧图像水平分割成多个窗口,并提取每个窗口内的视差关系,可以减少内存占用和运行时间。同时,我们还进一步进行了水平特征调制,以处理跨窗口的视差变化。其次,基于可变形卷积的运动配准模块(MAM)探索了独立视图特征空间中的时间相关性。最后,我们提出了雾自适应细化模块(FARM),用于在交互和配准后细化特征。FARM 结合了雾的先验信息,并指导网络动态生成处理内核进行去雾处理,以适应不同的雾场景。定量和定性结果表明,所提出的 PMCN 在合成和实际数据集上的表现都优于最先进的方法。此外,我们的 PMCN 还有利于提高雾场景中高级视觉任务(如物体检测和立体匹配)的准确性。
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
Knowledge-Based Systems
Knowledge-Based Systems 工程技术-计算机:人工智能
CiteScore
14.80
自引率
12.50%
发文量
1245
审稿时长
7.8 months
期刊介绍: Knowledge-Based Systems, an international and interdisciplinary journal in artificial intelligence, publishes original, innovative, and creative research results in the field. It focuses on knowledge-based and other artificial intelligence techniques-based systems. The journal aims to support human prediction and decision-making through data science and computation techniques, provide a balanced coverage of theory and practical study, and encourage the development and implementation of knowledge-based intelligence models, methods, systems, and software tools. Applications in business, government, education, engineering, and healthcare are emphasized.
×
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