摘要
数字壁画修复是计算机视觉在图像修复领域的一个重要应用。为解决修复过程中存在的模糊、结构紊乱、细节丢失等问题,提出了改进的双阶段生成对抗数字壁画修复模型。首先在第1阶段生成器中设计了特征优化融合策略,将编码器中不同尺度的特征进行优化并在解码器部分按比例融合,减少卷积过程中特征信息的丢失;然后在第2阶段生成器中用空洞残差模块代替空洞卷积,将小膨胀率的空洞卷积与残差模块结合,增大感受野的同时减少空洞的累积,有效缓解了修复产生的网格伪影现象。实验结果表明:与其他几种修复算法相比,该方法在敦煌壁画数据集上的视觉效果和客观指标均有明显优势,其中峰值信噪比平均提升了3~5 dB,结构相似度平均提升了2%~6%。
Digital mural inpainting is an important application of computer vision in the field of image inpainting.Digital mural inpainting model based on improved two-stage generative adversarial network was proposed to solve the problems of ambiguity,structure disorder and detail loss in the process of inpainting.Firstly,a feature optimization fusion strategy is designed in the first-stage generator.The features of different scales in the encoder are optimized and fused in the decoder in proportion to reduce the loss of feature information in the convolution process.Then,in the second-stage generator,the dailated residual module is used instead of the dailated convolution process,and the dailated convolution with small expansion rate is combined with the residual module to increase the receptive filed and reduce the accumulation of holes,which effectively alleviates the repaired grid artifact phenomenon.The experimental results show that the proposed method has obvious advantages in visual effects and tube indexes on the mural dataset compared with other restoration algorithms,in which the peak signal-to-noise ratio is improved by 3~5 dB on average,and the Structural Similarity is improved by 2%~6%on average.
作者
张双
杨帆
Zhang Shuang;Yang Fan(School of Electronic and Information Engineering,Hebei University of Technology,Tianjin 30040l,China)
出处
《电子测量技术》
北大核心
2023年第11期123-129,共7页
Electronic Measurement Technology
基金
国家重点研发计划智能机器人专项(2019YFB1312102)
河北省自然科学基金(F2019202364)项目资助。
关键词
壁画修复
特征优化融合
空洞残差
生成对抗网络
mural inpainting
feature optimal fusion
dailated residual network
generative adversarial network
