摘要
为解决现有图像修复算法因缺乏上下文信息和有效的感受野导致修复大面积随机破损时效果差且只能修复低分辨率图像的缺陷,提出了基于残差变换器的并行傅里叶卷积修复算法.首先,提出基于变换器的改进残差网络模块提取待修复图像的纹理特征;然后,设计并行快速傅里叶卷积模块增强损失图像的高度有效感受野捕捉结构信息;最后,提出门控双特征融合模块交换和结合图像的结构与纹理分量,融合上下文特征,改善生成纹理的细粒度.在两个公开数据集上进行定性和定量实验,实验结果表明:所提算法可有效修复结构复杂且纹理精细的随机不规则大面积破损区域,生成结构合理、纹理细腻和语义丰富的高保真图像,并能用于高分辨率图像的目标移除.
To solve of the defects of the existing image inpainting algorithms,such as the lack of contextual information and effective perceptual field,leading to poor performance when recovering large random damages and being restricted to low-resolution images,a parallel fast Fourier convolution generation inpainting algorithm based on residual transformer is proposed.Firstly,a transformer-based improved residual network module is proposed to extract the texture features from the image to be inpainted.Subsequently,a parallel fast Fourier convolution module is designed to enhance highly effective sensory field and capture the structural information from the corrupt areas.Finally,the gated dual-feature fusion module is developed to exchange and combine the structural and texture components of the images to fuse the contextual features and improve the fine-grained nature of the generated textures.Qualitative and quantitative experiments are conducted on two public datasets,and the experimental results show that the proposed algorithm can effectively restore random irregular large broken regions with complex structures and fine textures,generate high-fidelity images with reasonable structures,fine textures and rich semantics,and can be used for target removal of high-resolution images.
作者
李海燕
宋应清
郭磊
周丽萍
陈泉
LI Haiyan;SONG Yingqing;GUO Lei;ZHOU Liping;CHEN Quan(School of Information Science and Engineering,Yunnan University,Kunming 650050,China;Journal of Yunnan University(Natural Science Edition),Yunnan University,Kunming 650050,China;Faculty of Humanities,University of Artois,Arras 62000,France)
出处
《湖南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2023年第8期42-51,共10页
Journal of Hunan University:Natural Sciences
基金
国家自然科学基金资助项目(6226049,62166048)
云南省万人计划“云岭教学名师”项目
云南省高校重点实验室建设计划资助项目(202101AS070031)。
关键词
图像修复
残差变换器
并行傅里叶卷积
门控双特征融合
image inpainting
residual transformer
parallel fast Fourier convolutions
gated dual feature fusion
