您好，欢迎访问福建省农业科学院 机构知识库！
福建省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

DATDM: Dynamic attention transformer diffusion model for underwater image enhancement

文献类型： 外文期刊

作者： Hu, Wang 1 ; Chen, Shitu 1 ; Luo, Tuyan 2 ; Zhang, Lijun 1 ; Zhang, Hongjin 1 ; Liu, Zhixiang 4 ; Zhang, Shiwen 5 ; Xu, Jingxiang 1 ;

作者机构： 1.Shanghai Ocean Univ, Coll Engn Sci & Technol, Shanghai 201306, Peoples R China

2.Fujian Acad Agr Sci, Inst Agr Qual Stand & Testing Technol, Fuzhou 350003, Peoples R China

3.Shanghai Engn Res Ctr Marine Renewable Energy, Shanghai 201306, Peoples R China

4.Shanghai Ocean Univ, Coll Informat Technol, Shanghai 201306, Peoples R China

5.Hunan Univ Sci & Technol, Sch Comp Sci & Engn, Xiangtan 411201, Peoples R China

关键词： Diffusion model; Underwater image enhancement; Color correction; Dynamic attention transformer

期刊名称：ALEXANDRIA ENGINEERING JOURNAL （ 影响因子：6.8； 五年影响因子：6.1 ）

ISSN： 1110-0168

年卷期： 2025 年 126 卷

页码：

收录情况： SCI

摘要： Underwater image degradation presents complex challenges, significantly impairing the efficiency of underwater tasks. The mainstream underwater image enhancement (UIE) methods are roughly divided into traditional physics-based and data-driven deep-learning methods. However, physical model-based methods have poor generalization capabilities. Data-driven methods require high-quality training data and suffer from limited model stability. We propose a novel UIE framework, DATDM, to address the above limitations and improve degraded underwater images. We first introduce a color correction module (CCM) to strengthen the model's image restoration capabilities. On the other hand, we propose a novel dynamic attention transformer (DAT) denoising network with excellent performance. The proposed DAT denoising network utilizes a dynamic attention transformer mechanism that adaptively extracts feature information based on the complexity of the feature map, effectively capturing rich features while optimizing computational efficiency. The proposed DATDM method significantly outperforms the existing state-of-the-art methods, with peak signal-to-noise ratios of 24.05 and 27.39 and structural similarity index measures of 0.9233 and 0.9504 on the UIEB and LSUI datasets, respectively. The final experiments demonstrate that our DATDM achieves better performance and visual effects on UIE tasks.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：福建省农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台