高级检索
    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[J]. 计算机研究与发展. DOI: 10.7544/issn1000-1239.202220623
    引用本文: 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[J]. 计算机研究与发展. DOI: 10.7544/issn1000-1239.202220623
    Wang Zhenyan, Jiang Shengcheng, Song Qihong, Liu Bo, Bi Xiuli, Xiao Bin. Transformer-Based Image Restoration Method for Cultural Relics[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202220623
    Citation: Wang Zhenyan, Jiang Shengcheng, Song Qihong, Liu Bo, Bi Xiuli, Xiao Bin. Transformer-Based Image Restoration Method for Cultural Relics[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202220623

    基于Transformer的文物图像修复方法

    Transformer-Based Image Restoration Method for Cultural Relics

    • 摘要: 文物极易因为保存不当而导致部分结构或纹理缺失,而现有的图像修复技术由于受到先验信息和卷积操作的局限而无法直接应用于文物图像修复,为更合理地恢复文物图像原貌,提出了一种新的文物图像修复方法,将文物图像修复工作分为2个步骤:第1步使用Transformer进行粗略的图像重建并恢复连贯的结构;第2步使用卷积神经网络将粗略的重建图像进行上采样并恢复缺失区域的精细纹理. 考虑到目前国内外没有高质量的大型文物数据库,因此也提出了一个新的高质量大型文物图像数据库. 最终实验结果表明,在符合现实场景的破损修复实验和大面积破损修复实验中,修复效果在主观和客观评估中均优于当前图像修复算法. 同时,支持多元化输出,为修复人员提供多样化参考,极大提升了文物修复效率.

       

      Abstract: 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 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 a 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, it supports diversified output, which provides diverse references for restorers and improves the restoration efficiency.

       

    /

    返回文章
    返回