版权说明 操作指南
首页 > 成果 > 详情

Feature representation learning for image denoising

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:
Yuxuan Hu;Shichao Zhang*
通讯作者:
Shichao Zhang
作者机构:
School of Computer Science and Engineering, Central South University, Changsha, 410083, Hunan, China
[Shichao Zhang] Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, 541004, Guangxi, China
School of Computer Science and Technology, Changsha University of Science & Technology, Changsha, 410114, Hunan, China
[Yuxuan Hu] School of Computer Science and Engineering, Central South University, Changsha, 410083, Hunan, China<&wdkj&>Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, 541004, Guangxi, China<&wdkj&>School of Computer Science and Technology, Changsha University of Science & Technology, Changsha, 410114, Hunan, China
通讯机构:
[Shichao Zhang] G
Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, 541004, Guangxi, China
语种:
英文
期刊:
Neurocomputing
ISSN:
0925-2312
年:
2026
卷:
659
页码:
131787
基金类别:
CRediT authorship contribution statement Yuxuan Hu: Writing – original draft, Software, Methodology, acquisition, Formal analysis, Conceptualization. Shichao Zhang: Writing – review & editing, Supervision, Project administration, Methodology, acquisition, Conceptualization.
机构署名:
本校为其他机构
摘要:
Image denoising plays a vital role in enhancing image quality for various downstream vision tasks by learning robust feature representations that distinguish clean signals from noise. Recent advances in deep learning have enabled data-driven feature extraction but frequently face challenges such as spatial-channel feature redundancy, suboptimal fusion of multi-level features, and over-smoothing due to pixel-wise loss functions. To address these interconnected issues, this paper proposes the Perceptual Feature Learning Network (PFLN), a lightweight architecture explicitly designed for efficient...

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