基于多特征融合的图像修复算法  

Image inpainting algorithm based on multi-feature fusion

作　　者：蒋行国 黎明 Jiang Xingguo;Li Ming(School of Automation and Information Engineering,Sichuan University of Science&Engineering,Yibin 644000,China;Artificial Intelligence Key Laboratory of Sichuan Province,Yibin 644000,China)

机构地区：[1]四川轻化工大学自动化与信息工程学院,宜宾644000 [2]人工智能四川省重点实验室,宜宾644000

出　　处：《电子测量技术》2024年第18期80-88,共9页Electronic Measurement Technology

基　　金：四川轻化工大学人才引进项目(2019RC12)资助。

摘　　要：针对现有图像修复算法修复结果存在结构一致性差和纹理细节不足等问题,在生成对抗网络(GAN)的框架下,提出一种基于多特征融合的图像修复算法。首先,采用双编码-解码结构提取纹理和结构特征信息,并引入快速傅里叶卷积残差块,有效捕获全局上下文特征。然后,通过注意力特征融合(AFF)模块完成结构与纹理特征之间的信息交换,提高图像的全局一致性。并利用密集连接特征聚合(DCFA)模块在多个尺度上提取丰富的语义特征,进一步提升修复图像的一致性和准确性,以呈现更精细的内容。实验结果表明,在破损区域占比为40%~50%时,相较于最优对比算法,所提算法在CelebA-HQ数据集上PSNR和SSIM分别提高1.18%和0.70%,FID降低3.99%。在Paris StreetView数据集上PSNR和SSIM分别提高1.17%和0.50%,FID降低2.29%。实验证明所提算法能有效修复大面积破损图像,修复结果具有更合理的结构和丰富的纹理细节。Aiming at the problems of poor structural consistency and insufficient texture details in the inpainting results of existing image inpainting algorithms,an image inpainting algorithm based on multi-feature fusion was proposed under the framework of generative adversarial network(GAN).Firstly,the dual encoder-decoder structure is used to extract the texture and structure feature information,and the fast Fourier convolution residual block is introduced to effectively capture the global context features.Then,the information exchange between structure and texture features was completed through the attention feature fusion(AFF)module to improve the global consistency of the image.The dense connected feature aggregation(DCFA)module was used to extract rich semantic features at multiple scales to further improve the consistency and accuracy of the inpainted image,so as to present more detailed content.Experimental results show that,compared with the optimal comparison method,the proposed algorithm improves PSNR and SSIM by 1.18%and 0.70%respectively,and reduces FID by 3.99%on the Celeba-HQ dataset when the proportion of damaged regions is 40%~50%.On the Paris Street View dataset,PSNR and SSIM are increased by 1.17%and 0.50%,respectively,and FID is reduced by 2.29%.Experimentally,it is proved that the suggested algorithm can effectively repair large broken images,and the repaired images have a more sensible structure and richer texture details.

关 键 词：图像修复 生成对抗网络 多特征融合 快速傅里叶卷积残差块 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TN919.8[自动化与计算机技术—计算机科学与技术]