YNAO OpenIR  > 抚仙湖太阳观测站
自适应融合层级特征的混合退化图像复原算法
Alternative TitleMixed Degraded Image Restoration Algorithm Based on Adaptive Fusion of Hierarchical Features
白亮1; 刘辉1,2; 尚振宏1,3
Source Publication计算机辅助设计与图形学学报(Journal of Computer-Aided Design & Computer Graphics)
2020
DOI10.3724/SP.J.1089.2021.18482
ClassificationTP391.41
Contribution Rank第2完成单位
Indexed ByEI ; CSCD ; 核心
Keyword自适应复原 混合退化 层级特征融合 感知损失
Abstract

多种退化类型混合的图像比单一类型的退化图像降质更严重, 很难建立精确模型对其复原, 研究端到端的神经网络算法是复原的关键. 现有的基于操作选择注意力网络的算法(operation-wise attention network, OWAN)虽然有一定的性能提升, 但是其网络过于复杂, 运行较慢, 复原图像缺乏高频细节, 整体效果也有提升的空间. 针对这些问题, 提出一种基于层级特征融合的自适应复原算法. 该算法直接融合不同感受野分支的特征, 增强复原图像的结构; 用注意力机制对不同层级的特征进行动态融合, 增加模型的自适应性, 降低了模型冗余; 另外, 结合L1损失和感知损失, 增强了复原图像的视觉感知效果. 在DIV2K, BSD500等数据集上的实验结果表明, 该算法无论是在峰值信噪比和结构相似性上的定量分析, 还是在主观视觉质量方面, 均优于OWAN算法, 充分证明了该算法的有效性. 

Other Abstract

The degradation of mixed degraded images is more serious than that of single degradation types, and it is difficult to restore them by precise modeling. The key to restore mixed degraded images is to study the
end-to-end neural network algorithm. Although the existing operation-wise attention network (OWAN) algorithm has a certain performance improvement, its network is too complex, it runs slowly, the restored image lacks high-frequency details, and the overall effect also has room for improvement. To solve these problems, an adaptive restoration algorithm based on hierarchical feature fusion is proposed. The algorithm directly fuses the features of different receptive field branches to enhance the structure of the restored image. The attention mechanism is used to dynamically fuse the features of different hierarchies to increase the adaptability and reduce the redundancy of the model. In addition, combining the 1 L loss and perception loss, the visual perception effect of the restored image is enhanced. Experimental results on DIV2K, BSD500 and other data sets show that the proposed algorithm is better than the OWAN algorithm in terms of quantitative analysis of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), as well as subjective visual quality.

Funding Project国家自然科学基金[12063002] ; 国家自然科学基金[11873027] ; 国家自然科学基金[61462052]
Funding Organization国家自然科学基金[12063002, 11873027, 61462052]
Language中文
Subject Area计算机科学技术 ; 计算机应用
MOST Discipline Catalogue工学 ; 工学::计算机科学与技术(可授工学、理学学位)
ISSN1003-9775
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ynao.ac.cn/handle/114a53/23958
Collection抚仙湖太阳观测站
Affiliation1.昆明理工大学信息工程与自动化学院, 昆明, 650500
2.中国科学院云南天文台, 昆明, 650216
3.昆明理工大学云南省人工智能重点实验室, 昆明, 650500
Recommended Citation
GB/T 7714
白亮,刘辉,尚振宏. 自适应融合层级特征的混合退化图像复原算法[J]. 计算机辅助设计与图形学学报(Journal of Computer-Aided Design & Computer Graphics),2020.
APA 白亮,刘辉,&尚振宏.(2020).自适应融合层级特征的混合退化图像复原算法.计算机辅助设计与图形学学报(Journal of Computer-Aided Design & Computer Graphics).
MLA 白亮,et al."自适应融合层级特征的混合退化图像复原算法".计算机辅助设计与图形学学报(Journal of Computer-Aided Design & Computer Graphics) (2020).
Files in This Item:
File Name/Size DocType Version Access License
自适应融合层级特征的混合退化图像复原算法(870KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[白亮]'s Articles
[刘辉]'s Articles
[尚振宏]'s Articles
Baidu academic
Similar articles in Baidu academic
[白亮]'s Articles
[刘辉]'s Articles
[尚振宏]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[白亮]'s Articles
[刘辉]'s Articles
[尚振宏]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 自适应融合层级特征的混合退化图像复原算法_白亮.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.