级联迭代精细化的敦煌壁画图像修复
CSTR:
作者:
作者单位:

(兰州交通大学 电子与信息工程学院,兰州 730070)

作者简介:

曹岩(1982—),男,副教授,硕士生导师;邬开俊(1978—),男,教授,博士生导师

通讯作者:

邬开俊,wkj@mail.lzjtu.cn

中图分类号:

TP391.41

基金项目:

甘肃省自然科学基金(23JRRA913);内蒙古自治区重点研发与成果转化计划项目(2023YFSH3,3YFDZ0054)


Cascade iterative refinement of Dunhuang mural image inpainting
Author:
Affiliation:

(School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China)

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为解决破损敦煌壁画图像修复中存在的结构修复不合理及图像特征纹理不够细化的问题,提出一种级联迭代精细化壁画图像修复模型。该模型通过多层残差连接网络(multi residual-net,MR-Net)结合空间和通道注意力,利用迭代层归一化残差模块(layernorm residual module,LRM)及普通卷积进行先修复,逐步提取壁画图像的全局和局部特征信息;结合深度可分离卷积下的多头转置注意(dsconv layernorm transposed-attention,DSLT-A)和门控部分卷积特征聚合传播模块(feature aggregation propagation module,FAPM),对图像的全局信息和局部特征纹理信息进行重构;通过部分卷积多尺度门控模块增加修复过程中缺失的原始图像特征信息,对壁画图像的纹理信息进行细化。进行人为不规则掩码修复实验、模拟霉斑掩码修复实验以及真实破损壁画修复实验。实验结果表明:与4种对比模型中表现最好的数据相比,本文所提模型修复图像的 峰值信噪比提升了1.178 dB,结构相似性指数提升了0.010 2,平均平方损失函数降低了0.000 9,3种指标均优于对比模型。所提模型能够修复出更高质量的壁画图像,为提高敦煌壁画图像修复水平以及后续研究数字化敦煌壁画图像修复提供技术支撑和参考。

    Abstract:

    To address the issues of unreasonable structural inpainting and insufficiently refined image texture features in the inpainting of damaged Dunhuang mural images, this paper proposes a cascaded iterative fine-grained mural image inpainting model. This model utilizes a multi-layer residual-net (MR-Net) combined with spatial and channel attention mechanisms,and employs an iterative layernorm residual module (LRM) together with standard convolution for initial inpainting, progressively extracting both global and local feature information of the mural images. Subsequently, the dsconv layernorm teansposed-attention (DSLT-A) and the gated feature aggregation propagation module (FAPM) are combined to reconstruct the global and local texture features. A partial convolution multi-scale gating module is used to enhance missing original image feature information during the inpainting process, refining the texture information of the mural images. Experiments were conducted using artificially irregular mask inapinting, simulated mold spot mask restoration, and real damaged mural inpainting. The experiment results show that, under three objective evaluation metrics, compared with the best-performing data among four comparative models, the model proposed in this paper improves the peak signal-to-noise ratio of the inpainted images by 1.178 dB, structural similarity index by 0.010 2, and reduces mean squared loss by 0.000 9, all outperforming the other comparative models. The proposed model is capable of inpainting higher-quality mural images, providing technical support and reference for improving the inpainting level of Dunhuang mural images and promoting future research in digital inpainting of Dunhuang murals.

    参考文献
    相似文献
    引证文献
引用本文

曹岩,辛子昊,马宁,朱崇凯,邬开俊.级联迭代精细化的敦煌壁画图像修复[J].哈尔滨工业大学学报,2026,58(9):125. DOI:10.11918/202410044

复制
分享
相关视频

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-10-21
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2026-10-11
  • 出版日期:
文章二维码