版权说明 操作指南
首页 > 成果 > 详情

MLCTA-Net: multi-scale large convolution and triplet attention network for single image dehazing

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Tang, Qingshan;Miao, Yongqi;Huang, Xinwei;Jiang, Huang
通讯作者:
Tang, QS
作者机构:
[Miao, Yongqi; Huang, Xinwei; Tang, Qingshan; Jiang, Huang] Changsha Univ Sci & Technol, Sch Phys & Elect Sci, Muyun St, Changsha 410004, Hunan, Peoples R China.
通讯机构:
[Tang, QS ] C
Changsha Univ Sci & Technol, Sch Phys & Elect Sci, Muyun St, Changsha 410004, Hunan, Peoples R China.
语种:
英文
关键词:
Single image dehazing;Multi-scale feature;Parallel depth-wise large convolutions;Triplet attention
期刊:
Signal, Image and Video Processing
ISSN:
1863-1703
年:
2025
卷:
19
期:
5
页码:
1-9
基金类别:
Not applicable.
机构署名:
本校为第一且通讯机构
院系归属:
物理与电子科学学院
摘要:
Single image dehazing is a fundamental yet challenging task in computer vision. Many studies aim to improve learning-based methods by constructing deep residual networks with multiple small convolutional kernels and attention mechanisms. However, these methods encounter two major limitations. First, small convolutional kernels in redundant layers of deep residual networks may not train effectively, restricting the receptive field’s expansion. Second, haze impacts image information across three dimensions, necessitating consideration of their i...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com