计算机工程与应用2024，Vol.60Issue(1)：217-226,10.DOI:10.3778/j.issn.1002-8331.2207-0415
傅里叶变换下的粗细双路径图像修复算法
Coarse and Fine Dual Path Image Inpainting Algorithm Based on Fourier Transform
摘要
Abstract
In view of the weak ability of extracting global features and the frequency domain difference between the inpainted image and the original image in the traditional coarse and fine dual path image inpainting algorithm,causing the global structure of the repaired image to be poor,the coarse and fine dual path image inpainting algorithm based on Fourier transform is proposed.Firstly,in order to improve the ability of the encoder to extract features,an encoder based on squeeze and excitation model is designed to improve the ability of the network to collect global information.Secondly,the focal frequency loss is introduced for the first time to supervise image inpainting,and the frequency domain difference between the inpainted image and the original image is reduced,it improves the ability of the algorithm to inpaint high-frequency components,and artifacts and blurs are improved.Finally,the algorithm is applied to CelebA dataset.Compared with the images inpainted by the baseline algorithms,the peak signal-to-noise ratio(PNSR)and structural simi-larity(SSIM)of the images inpainted by the proposed algorithm are improved by 1.18%～6.14%and 0.11%～2.24%respec-tively.However,the distance score(FID)is decreased by 34.58%～38.78%.Experimental results show that the proposed algorithm achieves better performance improvement at a small time cost and enhances the global structure and clarity of the inpainted image.关键词
压缩奖惩块/傅里叶变换/焦频损失/图像修复Key words
squeeze and excitation model/Fourier transform/focal frequency loss/image inpainting分类
计算机与自动化引用本文复制引用
陈刚,盛况,杨振国,刘文印..傅里叶变换下的粗细双路径图像修复算法[J].计算机工程与应用,2024,60(1):217-226,10.基金项目
国家自然科学基金(62076073) （62076073）
广东省重大科技专项(2015B010126001) （2015B010126001）
广东省科技计划项目(202007040005). （202007040005）
