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
  • [1] Dadnet: dual-attention detection network for crack segmentation on tomb murals
    Wu, Meng
    Chai, Ruochang
    Zhang, Yongqin
    Lu, Zhiyong
    HERITAGE SCIENCE, 2024, 12 (01):
  • [2] Dual-Attention Mechanism for Monocular Depth Estimation
    Chiu, Chui-Hong
    Astuti, Lia
    Lin, Yu-Chen
    Hung, Ming-Ku
    2024 16TH INTERNATIONAL CONFERENCE ON COMPUTER AND AUTOMATION ENGINEERING, ICCAE 2024, 2024, : 456 - 460
  • [3] Quality assessment of abdominal CT images: an improved ResNet algorithm with dual-attention mechanism
    Zhu, Boying
    Yang, Yuanyuan
    AMERICAN JOURNAL OF TRANSLATIONAL RESEARCH, 2024, 16 (07): : 3099 - 3107
  • [4] Dual-Attention GAN for Large-Pose Face Frontalization
    Yin, Yu
    Jiang, Songyao
    Robinson, Joseph P.
    Fu, Yun
    2020 15TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2020), 2020, : 249 - 256
  • [5] Image Steganalysis Network Based on Dual-Attention Mechanism
    Zhang, Xuanbo
    Zhang, Xinpeng
    Feng, Guorui
    IEEE SIGNAL PROCESSING LETTERS, 2023, 30 : 1287 - 1291
  • [6] A Hybrid Improved Dual-Channel and Dual-Attention Mechanism Model for Water Quality Prediction in Nearshore Aquaculture
    Liu, Wenjing
    Wang, Ji
    Li, Zhenhua
    Lu, Qingjie
    ELECTRONICS, 2025, 14 (02):
  • [7] Tweet-aware News Summarization with Dual-Attention Mechanism
    Zheng, Xin
    Sun, Aixin
    Muthuswamy, Karthik
    WEB CONFERENCE 2021: COMPANION OF THE WORLD WIDE WEB CONFERENCE (WWW 2021), 2021, : 473 - 480
  • [8] Damage identification of frame structure based on CNN model with dual-attention mechanism and improved Inception module
    Liu, Jingliang
    Lu, Yulin
    Zheng, Wenting
    Liao, Feiyu
    Chen, Zongyan
    Zhendong yu Chongji/Journal of Vibration and Shock, 2024, 43 (23): : 321 - 328
  • [9] Tool wear prediction method based on dual-attention mechanism network
    Cheng, Yaonan
    Zhou, Shilong
    Lu, Mengda
    Xue, Jing
    Gai, Xiaoyu
    Guan, Rui
    INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING, 2024,
  • [10] Face Inpainting Based on Dual Self-attention Mechanism
    Yue H.
    Liao L.
    Yang J.
    Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences, 2023, 50 (08): : 32 - 41