基于上下文特征提取的边缘生成三阶段图像修复算法  

Three‑Stage Image Inpainting Algorithm by Edge Generation Based on Contextual Feature Extraction

作　　者：芮志超 郭艳艳[1] RUI Zhichao;GUO Yanyan(College of Physics and Electronic Engineering,Shanxi University,Taiyuan 030006,China)

机构地区：[1]山西大学物理电子工程学院,山西太原030006

出　　处：《测试技术学报》2024年第1期34-40,共7页Journal of Test and Measurement Technology

摘　　要：对于具有较大不规则缺失区域的图像修复问题,现有的基于深度学习的图像修复方法通常会生成具有模糊纹理和扭曲结构的内容。针对这个问题,将修复问题分解为基于上下文特征的结构预测和图像补全三阶段模型。第一阶段,通过空洞卷积编-解码网络,利用周围图像特征来对缺失部分进行初步修复;第二阶段,将第一阶段粗修复结果进行边缘提取后,输入到一个自注意力机制编-解码网络来预测缺失区域的纹理结构;第三阶段,将前两个阶段的输出一起输入到一个改进的U-net精修复网络中,得到结构清晰、纹理细节丰富的图像。在公开数据集上将所提算法与现有经典算法进行对比,实验表明,所提方法在主观视觉和客观评价方面优于现有方法。For an image of large irregular missing regions,recent deep learning-based image inpainting approaches often generate content with blurred textures and distorted structures.To solve these problems,a three-stage model that separates the inpainting problem into contextual feature-based structure prediction and image completion is proposed.In the first stage,our model utilizes surrounding image features to predict missing regions during a dilated convolutional encoder-decoder network training.In the second stage,an encoder-decoder network based on the self-attention mechanism takes edge features extracted from the first stage predictions as inputs and recovers the texture structure of the missing regions.In the third stage,the outputs of the first two stages are passed to a refined inpainting network using the improved Unet architecture to guide the repair process.The proposed algorithm is compared with the existing classic algorithm on the public datasets.Experiments show that our method outperforms existing methods in terms of subjective vision and objective evaluation.

关 键 词：深度学习 图像修复 自注意力机制 Res2net 生成式对抗网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]