| 基于空间通道注意力机制的渐进式图像超分辨重建算法 |
| |
| 引用本文： | 秦玉,谢超宇,王晓明.基于空间通道注意力机制的渐进式图像超分辨重建算法[J].西华大学学报(自然科学版),2022,41(2):39-50. |
| |
| 作者姓名： | 秦玉 谢超宇 王晓明 |
| |
| 作者单位： | 西华大学计算机与软件工程学院，四川 成都 610039 |
| |
| 基金项目： | 国家自然科学基金资助项目（61602390） |
| |
| 摘 要： | 目前在单帧图像超分辨率(SISR)研究领域中,一些深度网络在重构阶段通过简单级联、通道注意、空间注意等方式,利用中间特征来提高图像重构效果,但是它们通常只注意到其中一个方向.为此,文章研究了一种新的注意力,即基于空间特征变换(SFT)的空间通道注意力,并提出了基于SFT的空间通道注意力机制重构的渐进式网络算法.该算法多...
|
| 关 键 词： | 注意力机制 空间特征变换 渐进式上采样 超分辨率 深度学习 |
| 收稿时间： | 2021-08-24 |
A Progressive Image Super-resolution Reconstruction Algorithm Based on the Spatial Channel Attention Mechanism |
| |
| QIN Yu,XIE Chaoyu,WANG Xiaoming.A Progressive Image Super-resolution Reconstruction Algorithm Based on the Spatial Channel Attention Mechanism[J].Journal of Xihua University:Natural Science Edition,2022,41(2):39-50. |
| |
| Authors: | QIN Yu XIE Chaoyu WANG Xiaoming |
| |
| Affiliation: | School of Computer and Software Engineering, Xihua University, Chengdu 610039 China |
| |
| Abstract: | Presently, in the field of single-frame image super-resolution (SISR), some deep networks are used to improve the image reconstruction effect through some intermediate features, such as simple cascading, channel attention, spatial attention, etc. in the reconstruction stage. However, people usually only pay attention to one of the directions. In this paper, the spatial channel attention based on SFT, and a progressive network are proposed, which based on the reconstruction of the spatial channel attention mechanism of spatial feature transform(SFT). The network uses intermediate features for image reconstruction from multiple angles. Firstly, it provides more similarity features based on SFT during feature extraction, and then it uses SFT spatial channel attention module (SFTCA module) to provide channel contribution strength and spatial dependence for image reconstruction. The experimental results show that, compared with most super-resolution algorithms, the proposed method has greatly improved the evaluation indexes during image super-resolution reconstruction, and the texture information of the reconstructed image is also clearer. |
| |
| Keywords: | |
|
| 点击此处可从《西华大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《西华大学学报(自然科学版)》下载全文 |
|
