测试技术学报2024，Vol.38Issue(3)：274-280,7.DOI:10.3969/j.issn.1671-7449.2024036
基于纹理和结构的双流人脸图像修复算法
Two-Stream Face Image Restoration Algorithm Based on Texture and Structure
王贺 1宋宏旭 1张震1
作者信息
- 1. 山西大学 物理电子工程学院,山西 太原 030006
- 折叠
摘要
Abstract
As an important research direction in the field of image processing,image restoration has attracted much attention.The existing image restoration models only focus on one aspect of texture or structure,but ignore that the two complement each other in image restoration tasks,which leads to unsat-isfactory images.In this paper,the codecs of double tributaries are used as the backbone of the image gen-erator,corresponding to the texture features and structure features of the generated image respectively,so as to achieve the effect of structure constraint texture and texture guidance structure.Secondly,The bidi-rectional residual feature fusion module is used to fuse texture features and structure features generated by the decoder to complete the information exchange of the two features.Finally,The detailed features of the restored images are enriched with a multi-scale context feature information aggregation module.Experi-ments show that the proposed method can improve the SSIM and PSNR values under different mask rates.关键词
图像修复/深度学习/纹理和结构特征/双向残差特征融合/上下文特征信息聚合Key words
image restoration/deep learning/texture and structural features/bidirectional residual feature fusion/contextual feature information aggregation分类
信息技术与安全科学引用本文复制引用
王贺,宋宏旭,张震..基于纹理和结构的双流人脸图像修复算法[J].测试技术学报,2024,38(3):274-280,7.
