收藏切换
Transformer-Based Image Restoration Method for Cultural Relics
收藏切换
Zhenyan Wang, Shengcheng Jiang, Qihong Song, Bo Liu*, Xiuli Bi, Bin Xiao
Journal of Computer Research and Development | 2024, 61(3) : 748 - 761
Less
收藏切换
Journal of Computer Research and Development | 2024, 61(3): 748-761
• Graphics and Image Processing •
Transformer-Based Image Restoration Method for Cultural Relics
Full
Zhenyan Wang, Shengcheng Jiang, Qihong Song, Bo Liu*, Xiuli Bi, Bin Xiao
Affiliations
  • 1Chongqing Key Laboratory of Image Cognition(Chongqing University of Posts and Telecommunications), Chongqing 400065
  • born in 1999. Bachelor. His main research interest includes image processing

    born in 2000. Bachelor. His main research interest includes image processing

    born in 2001. Bachelor. His main research interest includes image processing

    born in 1987. PhD, lecturer. Member of CCF. His main research interests include image processing and multimedia forensics

    born in 1982. PhD, associate professor, PhD supervisor. Member of CCF. Her main research interests include image processing and multimedia information security

    born in 1982. PhD, professor, PhD supervisor. Member of CCF. His main research interests include image processing and pattern recognition

About Author:

born in 1999. Bachelor. His main research interest includes image processing

born in 2000. Bachelor. His main research interest includes image processing

born in 2001. Bachelor. His main research interest includes image processing

born in 1987. PhD, lecturer. Member of CCF. His main research interests include image processing and multimedia forensics

born in 1982. PhD, associate professor, PhD supervisor. Member of CCF. Her main research interests include image processing and multimedia information security

born in 1982. PhD, professor, PhD supervisor. Member of CCF. His main research interests include image processing and pattern recognition

Published: 2024-03-02 doi: 10.7544/issn1000-1239.202220623
Outline
收藏切换

Cultural relics are prone to partial losses of structure or texture due to improper preservation. In order to restore the original image of cultural relics, we propose a new method for restoring cultural relics by using Transformer’s global structure understanding ability to restore the coherent structure of cultural relics and using convolutional neural networks’ local texture understanding ability to restore the delicate texture of cultural relics. To achieve this goal, the restoration work is divided into two steps: the first step is to use Transformer to reconstruct the rough image and restore the coherent structure; the second step is to use a convolutional neural network to enlarge the rough image and restore the fine texture of the missing area. Considering that there is no high-quality, large-scale heritage database in China and abroad, a new heritage image database is also proposed. The experimental results show that the restoration results outperform the current image restoration algorithms in both subjective and objective evaluations in both breakage restoration experiments and large-area breakage restoration experiments that match realistic scenes. At the same time, the proposed method supports diversified output, which provides diverse references for restorers and improves the restoration efficiency.

cultural relic database  /  cultural relic image completion  /  Transformer  /  convolutional neural networks  /  super-resolution  /  virtual restoration
王真言, 蒋胜丞, 宋奇鸿, 刘波, 毕秀丽, 肖斌. 基于Transformer的文物图像修复方法. 计算机研究与发展, 2024 , 61 (3) : 748 -761 . DOI: 10.7544/issn1000-1239.202220623
Zhenyan Wang, Shengcheng Jiang, Qihong Song, Bo Liu, Xiuli Bi, Bin Xiao. Transformer-Based Image Restoration Method for Cultural Relics[J]. Journal of Computer Research and Development, 2024 , 61 (3) : 748 -761 . DOI: 10.7544/issn1000-1239.202220623
Year 2024 volume 61 Issue 3
78
36
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202220623
  • Receive Date:2022-07-07
  • Online Date:2026-11-17
  • Published:2024-03-02
Article Data
Affiliations
History
  • Received:2022-07-07
  • Revised:2023-06-30
Affiliations
    1Chongqing Key Laboratory of Image Cognition(Chongqing University of Posts and Telecommunications), Chongqing 400065
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202220623
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT