摘要
针对已有去雨网络在不同环境中去雨不彻底和图像细节信息损失严重的问题,本文提出一种基于注意力机制的多分支特征级联图像去雨网络。该模型结合多种注意力机制,形成不同类型的多分支网络,将图像空间细节和上下文特征信息在整体网络中自下而上地进行传递并级联融合,同时在网络分支间构建的阶段注意融合机制,可以减少特征提取过程中图像信息的损失,更大限度地保留特征信息,使图像去雨任务更加高效。实验结果表明,本文算法的客观评价指标优于其他对比算法,主观视觉效果得以有效提升,去雨能力更强,准确性更加突出,能够去除不同密度的雨纹,并且能够更好地保留图像背景中的细节信息。
This paper proposes a multi-branch feature cascade image deraining network based on the attention mechanism to address the problems that existing deraining networks do not entirely deraining in diverse environments and do not adequately preserve image texture details.The model combines multiple attention mechanisms to form multi-branch networks to transfer and cascade the spatial image details and contextual feature information in the overall network and fuse them.Moreover, the stage attention fusion mechanism constructed between network branches can reduce the loss of image information during feature extraction and retain feature information to a greater extent, making the image deraining task more effective.The experimental results demonstrate that the new algorithm outperforms other comparison algorithms in terms of objective evaluation indices, the subjective visual effect can be effectively enhanced, the deraining ability is more substantial, the accuracy is more remarkable, and it can remove various densities of rain patterns while preserving the image's detail information.
作者
宋玉琴
赵继涛
商纯良
SONG Yuqin;ZHAO Jitao;SHANG Chunliang(School of Electronic Information,Xi'an Polytechnic University,Xi'an,Shaanxi 710048,China)
出处
《光电子．激光》
CAS
CSCD
北大核心
2024年第4期379-387,共9页
Journal of Optoelectronics·Laser
基金
中国纺织工业联合会科技指导性项目(2019062)
西安市科技局计划项目(201905030YD8CG14)资助项目。
关键词
图像去雨
多分支网络
注意力机制
级联融合
阶段注意融合机制
image removal rain
multi-branch network
attention mechanism
cascade fusion
stage at-tention fusion mechanism
