多尺度双注意力的图像超分辨率重建方法
Multi-scale Dual Attention Image Super-resolution Reconstruction Method
王鑫 1余磊1
作者信息
- 1. 重庆师范大学计算机与信息科学学院,重庆 401331
- 折叠
摘要
针对当前已有的图像超分辨率重建方法存在提取的特征信息单一、特征利用率低等问题,提出一种多尺度双注意力的图像超分辨率重建方法(MSDA).首先,该方法通过多尺度特征提取块,提取输入图像不同尺度的特征信息;其次,引入双注意力机制使网络快速关注图像高频信息区域,利用跳跃连接来减少特征信息在深层次网络递进过程中的信息丢失;最后,使用dropout层来均衡化特征通道重要性,防止网络协同适应,提升模型的泛化性.在公共测试集Set5、Set14、BSD100、Urban100、Manga109上的实验结果表明:MSDA取得了较好的效果,重建后的图像具有更多高频信息,纹理细节丰富,观感上更接近原始高分辨率图像.
Abstract
Addressing the issues of limited feature information extraction and low feature utilization in existing image super-resolution reconstruction methods,we propose a Multi-Scale Dual Attention(MSDA)approach.Firstly,this method employs multi-scale feature extraction blocks to capture feature information from different scales of the input image.Subsequently,a dual attention mechanism is introduced to enable the network to rapidly focus on high-frequency regions in the images,while utilizing skip connections to mitigate feature information loss during deep network propagation.Lastly,a dropout layer is employed to bal-ance the importance of feature channels,preventing network co-adaptation,and enhancing the model's generalization capabil-ity.Experimental results on public test datasets,including Set5,Set14,BSD100,Urban100,and Manga109,demonstrate that MSDA achieves superior performance by generating images with enhanced high-frequency information,enriched texture details,and a perceptual resemblance to the original high-resolution images.
关键词
超分辨率/多尺度特征/双注意力/跳跃连接Key words
super-resolution/multi-scale features/dual attention/jump connection引用本文复制引用
基金项目
国家自然科学基金面上项目(72071019)
重庆市自然科学基金面上项目(cstc2021jcyjmsxmX0185)
出版年
2024
国家科技期刊平台
NSTL
万方数据