首页|基于感知去模糊的高分辨率破损图像修复方法

基于感知去模糊的高分辨率破损图像修复方法

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
为提高修复图像的视觉效果,提出基于感知去模糊的高分辨率破损图像修复方法.将高分辨率图像样本输入卷积自编码生成对抗网络中,利用编码器降维处理并输出其低维特征矩阵后,由解码器对其升维并解码,最终采用生成器完成映射学习.通过不断搜寻,获得与输入高分辨率图像L1 距离差异最小的生成图像,由判别网络对其作真假判断,实现高分辨率破损图像的粗修复后,再将其输入感知去模糊网络模型中,增强图像细节信息后实现高分辨率图像修复.实验结果表明:该方法修复后的高分辨率图像细节丰富、颜色自然、视觉效果突出.
High Resolution Damaged Inpainting Method Based on Perceptual Deblurring
To improve the visual effect of repaired images,a high-resolution damaged image restoration method based on perceptual deblurring is proposed.Using high-resolution image samples as the input for convolutional self encoding to generate adversarial networks,the encoder is used to reduce the dimensionali-ty and output its low dimensional feature matrix.After that,the decoder increases the dimensionality and de-codes it.Finally,the generator is used to complete mapping learning.By continuously searching for the generated image with the smallest distance difference from the input high-resolution image L1,the discrimi-nant network determines whether it is true or false.After the coarse repair of the high-resolution damaged image,it is used as input to the perceptual deblurring network model to enhance image detail information and achieve high-resolution image restoration.The experimental results show that the high-resolution images repaired by this method have rich details,natural colors,and outstanding visual effects.

perceptual deblurringhigh resolution damaged imagefeature matrix spacerough re-pairL1 distance differencetrue or false judgment

濮毅

展开 >

马鞍山职业技术学院电子信息系,安徽 马鞍山 243031

感知去模糊 高分辨率破损图像 特征矩阵空间 粗修复 L1距离差异 真假判断

安徽省教育厅高等学校省级质量工程项目安徽省教育厅高等学校省级质量工程项目安徽省教育厅高等学校省级质量工程项目

2022jyxm15772022cjrh0462021jxtd286

2024

10.3969/j.issn.1671-0436.2024.02.002

常州工学院学报
常州工学院

常州工学院学报

影响因子：0.274
ISSN：1671-0436
年,卷(期)：2024.37(2)
  • 10