摘要
为了解决图像修复过程中破损区域信息丢失问题并实现图像中任意破损区域的修复,设计了双编码器模型,独立地对掩模和图像进行编码,利用掩模特征重建图像,减少掩模信息的损失,添加跳跃连接补充因下采样丢失的图像信息并加速网络的收敛,引入对抗训练提高重建图像的质量。在places2数据集上进行的训练和测试结果表明,该方法的图像修复效果在精度和全局性上均有良好的表现,且可用于多种类型掩模的图片修复。
In order to solve the problem of information loss in the damaged area during image restoration and to repair any damaged area in the image,a dual-encoder model is designed to independently encode the mask and image,reconstruct the image using the mask features,and reduce the mask information loss,adding skip connections to supplement image information loss due to down sampling and accelerate network convergence,introducing adversarial training to improve the quality of reconstructed images.The training and testing results on the places2 dataset show that the image restoration effect of this method has good performance in accuracy and globality,and can be used for image restoration of various types of masks.
作者
李健
孙大松
张备伟
LI Jian;SUN Dasong;ZHANG Beiwei(Office of Educational Administration,School of Information Engineering,Nanjing University of Finance&Economics,Nanjing 210023,China)
出处
《计算机工程与应用》
CSCD
北大核心
2021年第7期192-197,共6页
Computer Engineering and Applications
基金
国家自然科学基金(60802087)
江苏省研究生科研与实践创新计划(KYCX19_1384)。
关键词
图像修复
深度学习
生成式对抗网络
双编码器
跳跃连接
image restoration
deep learning
Generative Adversarial Network(GAN)
dual-encoder
skip connections
