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
  • [41] Research on out-of-sample prediction method of water quality parameters based on dual-attention mechanism
    Zheng, Zhiqiang
    Ding, Hao
    Weng, Zhi
    Wang, Lixin
    ENVIRONMENTAL MODELLING & SOFTWARE, 2024, 176
  • [42] FruitVision: Dual-Attention Embedded AI System for Precise Apple Counting Using Edge Computing
    Thakur, Divyansh
    Kumar, Vikram
    IEEE Transactions on AgriFood Electronics, 2024, 2 (02): : 445 - 459
  • [43] Image Inpainting of Thangka Murals Using Edge-Assisted Feature Fusion and Self Attention Based Local Refine Network
    Jia, Ying
    Li, Hang
    Fang, Jie
    Chen, Xin
    Ji, Liqi
    Wang, Nianyi
    IEEE ACCESS, 2023, 11 : 84360 - 84370
  • [44] Identifying technology opportunity using dual-attention model and technology-market concordance matrix*
    Motohashi, Kazuyuki
    Zhu, Chen
    TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE, 2023, 197
  • [45] U-Net with Coordinate Attention and VGGNet: A Grape Image Segmentation Algorithm Based on Fusion Pyramid Pooling and the Dual-Attention Mechanism
    Yi, Xiaomei
    Zhou, Yue
    Wu, Peng
    Wang, Guoying
    Mo, Lufeng
    Chola, Musenge
    Fu, Xinyun
    Qian, Pengxiang
    AGRONOMY-BASEL, 2024, 14 (05):
  • [46] CS-MRI Reconstruction Using an Improved GAN with Dilated Residual Networks and Channel Attention Mechanism
    Li, Xia
    Zhang, Hui
    Yang, Hao
    Li, Tie-Qiang
    SENSORS, 2023, 23 (18)
  • [47] DAU-Net: An unsupervised 3D brain MRI registration model with dual-attention mechanism
    Yang, Tiejun
    Bai, Xinhao
    Cui, Xiaojuan
    Gong, Yuehong
    Li, Lei
    INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY, 2023, 33 (01) : 217 - 229
  • [48] A Deep-Learning Method for Remaining Useful Life Prediction of Power Machinery via Dual-Attention Mechanism
    Wang, Fan
    Liu, Aihua
    Qu, Chunyang
    Xiong, Ruolan
    Chen, Lu
    SENSORS, 2025, 25 (02)
  • [49] Hyperspectral remote sensing identification of marine oil spills and emulsions using feature bands and double-branch dual-attention mechanism network
    Zhang, Ning
    Yang, Junfang
    Liu, Shanwei
    Ma, Yi
    Zhang, Jie
    JOURNAL OF OCEANOLOGY AND LIMNOLOGY, 2024, 42 (03) : 728 - 743
  • [50] Hyperspectral remote sensing identification of marine oil spills and emulsions using feature bands and double-branch dual-attention mechanism network
    Ning ZHANG
    Junfang YANG
    Shanwei LIU
    Yi MA
    Jie ZHANG
    Journal of Oceanology and Limnology, 2024, 42 (03) : 728 - 743