Fragments Inpainting for Tomb Murals Using a Dual-Attention Mechanism GAN with Improved Generators

被引:4
|
作者
Wu, Meng [1 ,2 ]
Chang, Xiao [1 ]
Wang, Jia [3 ]
机构
[1] Xian Univ Architecture & Technol, Sch Informat & Control Engn, Xian 710055, Peoples R China
[2] Xian Univ Architecture & Technol, Inst Interdisciplinary & Innovate Res, Xian 710055, Peoples R China
[3] Shaanxi Hist Museum, Xian 710061, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 06期
基金
中国国家自然科学基金;
关键词
multiscale feature aggregation; double attention; GAN; image inpainting; tomb mural; RESTORATION; IMAGE; PAINTINGS; NETWORK;
D O I
10.3390/app13063972
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
As the only underground mural in the collection, the tomb murals are subject to damage due to temperature, humidity, and foundation settlement changes. Traditional mural inpainting takes a long time and requires experts to draw it manually. Therefore, the need for digital inpainting is increasing to save time and costs. Due to the scarcity of samples and the variety of damage, the image features are scattered and partially sparse, and the colors are less vivid than in other images. Traditional deep learning inpainting causes information loss and generates irrational structures. The generative adversarial network is, recently, a more effective method. Therefore, this paper presents an inpainting model based on dual-attention multiscale feature aggregation and an improved generator. Firstly, an improved residual prior and attention mechanism is added to the generator module to preserve the image structure. Secondly, the model combines spatial and channel attention with multiscale feature aggregation to change the mapping network structure and improve the inpainting accuracy. Finally, the segmental loss function and its training method are improved.The experimental results show that the results of using signal-to-noise ratio (PSNR), structural similarity (SSIM), and mean square error (MSE) on epitaxial mask, crack mask, random small mask, and random large mask are better than other methods. It demonstrates the performance of this paper in inpainting different diseases of murals. It can be used as a reference for experts in manual inpainting, saving the cost and time of manual inpainting.
引用
收藏
页数:19
相关论文
共 50 条
  • [21] Spatial-Temporal Feature with Dual-Attention Mechanism for Encrypted Malicious Traffic Detection
    Liu, Jianyi
    Wang, Lanting
    Hu, Wei
    Gao, Yating
    Cao, Yaofu
    Lin, Bingjie
    Zhang, Ru
    SECURITY AND COMMUNICATION NETWORKS, 2023, 2023
  • [22] Multi-step ahead wind power forecasting based on dual-attention mechanism
    Aslam, Muhammad
    Kim, Jun-Sung
    Jung, Jaesung
    ENERGY REPORTS, 2023, 9 : 239 - 251
  • [23] SCA-Net: A Multiscale Building Segmentation Network Incorporating a Dual-Attention Mechanism
    Yu, Mingyang
    Zhang, Wenzhuo
    Chen, Xiaoxian
    Xu, Haiqing
    Liu, Yaohui
    IEEE ACCESS, 2022, 10 : 79890 - 79903
  • [24] WiGRUNT: WiFi-Enabled Gesture Recognition Using Dual-Attention Network
    Gu, Yu
    Zhang, Xiang
    Wang, Yantong
    Wang, Meng
    Yan, Huan
    Ji, Yusheng
    Liu, Zhi
    Li, Jianhua
    Dong, Mianxiong
    IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS, 2022, 52 (04) : 736 - 746
  • [25] Terrain Segmentation in Polarimetric SAR Images Using Dual-Attention Fusion Network
    Xiao, Daifeng
    Wang, Zhirui
    Wu, Youming
    Gao, Xin
    Sun, Xian
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [26] Hand acupuncture point localization method based on a dual-attention mechanism and cascade network model
    Wang, Hao
    Liu, Li
    Wang, Ying
    Du, Senhao
    BIOMEDICAL OPTICS EXPRESS, 2023, 14 (11) : 5965 - 5978
  • [27] Segmentation of Intracranial Aneurysm Remnant in MRA using Dual-Attention Atrous Net
    Banerjee, Subhashis
    Dhara, Ashis Kumar
    Wikstrom, Johan
    Strand, Robin
    2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 9265 - 9272
  • [28] A Dual-Attention Mechanism Deep Learning Network for Mesoscale Eddy Detection by Mining Spatiotemporal Characteristics
    Li, Baixin
    Tang, Huan
    Ma, Dongfang
    Lin, Jianmin
    JOURNAL OF ATMOSPHERIC AND OCEANIC TECHNOLOGY, 2022, 39 (08) : 1115 - 1128
  • [29] Deletion variants calling in third-generation sequencing data based on a dual-attention mechanism
    Wang, Han
    Li, Chang
    Yu, Xinyu
    Gao, Jingyang
    BRIEFINGS IN BIOINFORMATICS, 2024, 25 (04)
  • [30] Fabric pilling image segmentation by embedding dual-attention mechanism U-Net network
    Yan, Yu
    Tan, Yanjun
    Gao, Pengfu
    Yu, Qiuyu
    Deng, Yuntao
    TEXTILE RESEARCH JOURNAL, 2024, 94 (21-22) : 2434 - 2444