Frequency-Driven Diffusion: A Hierarchical Attention Weighting Framework for Underwater Image Restoration

IF 1.8 4区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Longxiang Deng, Laibin Chang, Wei Liu
{"title":"Frequency-Driven Diffusion: A Hierarchical Attention Weighting Framework for Underwater Image Restoration","authors":"Longxiang Deng,&nbsp;Laibin Chang,&nbsp;Wei Liu","doi":"10.1111/coin.70095","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>Underwater images often suffer from visual degradation, affecting downstream tasks. While recent underwater image enhancement (UIE) techniques have made some advances benefiting from deep neural networks, challenges remain in restoring fine details and achieving computational efficiency. Inspired by the success of diffusion models in image generation, we propose the Underwater Laplacian-Guided Diffusion Model (ULDM), which enhances image features layer-by-layer based on the hierarchical structure of the Laplacian pyramid transform to achieve both high-quality and efficient UIE. The Laplacian pyramid decomposes the degraded image into high- and low-frequency components, enabling the model to denoise the low-frequency spectrum and address global image degradation, thereby reducing computational overhead. To efficiently enhance high-frequency details, we introduce the Hierarchical Attention Weighted Module (HAWM) that leverages the strong pixel correlations in high-frequency sub-images at different levels, adjusting them layer-by-layer to better capture fine details. These high-frequency sub-images exhibit strong pixel correlation and consistent texture features across different layers, and their hierarchical pattern ensures effective detail restoration. Extensive experiments demonstrate that ULDM outperforms state-of-the-art methods in both quantitative and qualitative evaluations.</p>\n </div>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 4","pages":""},"PeriodicalIF":1.8000,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computational Intelligence","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/coin.70095","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Underwater images often suffer from visual degradation, affecting downstream tasks. While recent underwater image enhancement (UIE) techniques have made some advances benefiting from deep neural networks, challenges remain in restoring fine details and achieving computational efficiency. Inspired by the success of diffusion models in image generation, we propose the Underwater Laplacian-Guided Diffusion Model (ULDM), which enhances image features layer-by-layer based on the hierarchical structure of the Laplacian pyramid transform to achieve both high-quality and efficient UIE. The Laplacian pyramid decomposes the degraded image into high- and low-frequency components, enabling the model to denoise the low-frequency spectrum and address global image degradation, thereby reducing computational overhead. To efficiently enhance high-frequency details, we introduce the Hierarchical Attention Weighted Module (HAWM) that leverages the strong pixel correlations in high-frequency sub-images at different levels, adjusting them layer-by-layer to better capture fine details. These high-frequency sub-images exhibit strong pixel correlation and consistent texture features across different layers, and their hierarchical pattern ensures effective detail restoration. Extensive experiments demonstrate that ULDM outperforms state-of-the-art methods in both quantitative and qualitative evaluations.

频率驱动扩散:一种用于水下图像恢复的分层注意加权框架
水下图像经常受到视觉退化的影响,影响下游任务。虽然最近的水下图像增强(UIE)技术得益于深度神经网络取得了一些进展,但在恢复细节和实现计算效率方面仍然存在挑战。受扩散模型在图像生成中的成功启发,我们提出了水下拉普拉斯引导扩散模型(ULDM),该模型基于拉普拉斯金字塔变换的分层结构逐层增强图像特征,以实现高质量和高效的UIE。拉普拉斯金字塔将退化图像分解为高频和低频分量,使模型能够去噪低频频谱并解决全局图像退化问题,从而减少计算开销。为了有效地增强高频细节,我们引入了分层注意加权模块(HAWM),该模块利用不同级别高频子图像中的强像素相关性,逐层调整它们以更好地捕获细节。这些高频子图像具有较强的像素相关性和跨层一致的纹理特征,其分层模式确保了有效的细节恢复。广泛的实验表明,ULDM在定量和定性评估方面都优于最先进的方法。
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
Computational Intelligence
Computational Intelligence 工程技术-计算机:人工智能
CiteScore
6.90
自引率
3.60%
发文量
65
审稿时长
>12 weeks
期刊介绍: This leading international journal promotes and stimulates research in the field of artificial intelligence (AI). Covering a wide range of issues - from the tools and languages of AI to its philosophical implications - Computational Intelligence provides a vigorous forum for the publication of both experimental and theoretical research, as well as surveys and impact studies. The journal is designed to meet the needs of a wide range of AI workers in academic and industrial research.
×
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:604180095
Book学术官方微信