计算机应用与软件2025，Vol.42Issue(6)：265-271,7.DOI:10.3969/j.issn.1000-386x.2025.06.034
融合边缘信息的并行图像修复算法
PARALLEL IMAGE INPAINTING ALGORITHM COMBINING EDGE INFORMATION
摘要
Abstract
Existing image inpainting methods still have problems such as edge confusion,missing texture or incoherent repair distortion.Aimed at the above problems,a parallel generative adversarial inpainting network fused with edge structure is proposed.An edge structure repair network was designed to obtain the complete edge structure information,and the damaged image and edge structure information were sent to the parallel network structure based on gate convolution,respectively,through the improved contextual attention module and the multi-scale fusion block.Each branch extracted information to finally repair the image.The experimental results on Paris StreetView and CelebA-HQ datasets show that the method is basically better than the comparison algorithm in PSNR and SSIM,and the improvement is significantly improved by 6.2％and 5.5％on average under the large proportion of missing masks,which achieves realistic restoration results.关键词
边缘信息/多尺度融合块/门卷积/感知注意力/图像修复Key words
Edge information/Multi-scale fusion block/Gated convolution/Contextual attention/Image inpainting分类
信息技术与安全科学引用本文复制引用
文瑞森,原玲..融合边缘信息的并行图像修复算法[J].计算机应用与软件,2025,42(6):265-271,7.基金项目
广东省自然科学基金面上项目(2021A1515011341) （2021A1515011341）
