版权说明 操作指南
首页 > 成果 > 详情

High-resolution image reflection removal by Laplacian-based component-aware transformer

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:
"Chen, Songnan;Feng, Zhaoxu"
通讯作者:
Feng, Zhaoxu
作者机构:
["Chen, Songnan] School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, Hubei, China
["Chen, Songnan] Foshan Zhongke Innovation Research Institute of Intelligent Agriculture and Robotics, Foshan, Guangdong, China
[Feng, Zhaoxu"] China United Network Communications Co., Ltd. Henan Branch, Zhengzhou, Henan, China. iefengzhaoxu@163.com
通讯机构:
[Feng, Zhaoxu] C
China United Network Communications Co., Ltd. Henan Branch, Zhengzhou, Henan, China.
语种:
英文
期刊:
Scientific Reports
ISSN:
2045-2322
年:
2025
卷:
15
期:
1
页码:
9972
机构署名:
本校为第一机构
院系归属:
数学与计算机学院
摘要:
Recent data-driven deep learning methods for image reflection removal have made impressive progress, promoting the quality of photo capturing and scene understanding. Due to the massive consumption of computational complexity and memory usage, the performance of these methods degrades significantly while dealing with high-resolution images. Besides, most existing methods for reflection removal can only remove reflection patterns by downsampling the input image into a much lower resolution, resulting in the loss of plentiful information. In this paper, we propose a novel transformer-based frame...

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