自适应卷积约束与全局上下文推理的墓室壁画修复  

Tomb mural inpainting with adaptive convolutional constraints and global context inference

作　　者：吴萌[1,2] 郭歌 孙增国[3] 路智勇 张倩文 Wu Meng;Guo Ge;Sun Zengguo;Lu Zhiyong;Zhang Qianwen(School of Information and Control Engineering,Xi’an University of Architecture and Technology,Xi’an 710055,China;School of Institute for Interdisciplinary and Innovate Research,Xi’an University of Architecture and Technology,Xi’an 710055,China;School of Computer Science,Shaanxi Normal University,Xi’an 710119,China;Shaanxi History Museum,Xi’an 710061,China)

机构地区：[1]西安建筑科技大学信息与控制工程学院,西安710055 [2]西安建筑科技大学交叉创新研究院,西安710055 [3]陕西师范大学计算机科学学院,西安710119 [4]陕西历史博物馆,西安710061

出　　处：《中国图象图形学报》2025年第3期737-754,共18页Journal of Image and Graphics

基　　金：国家重点研发计划资助(2023YFC3803900);国家自然科学基金项目(62377033);西安建筑科技大学交叉研究培育专项(X2022082,X20230085)。

摘　　要：目的墓室壁画作为地下文物,由于环境湿度、地仗沉降等因素,局部区域出现了脱落、裂缝、霉变等多种病害,导致画面部分缺失。但现有深度学习的修复方法通常在单一维度或固定区域进行信息重建,无法充分捕获稀疏的壁画特征和修复多样化的复杂病害,修复时会出现内容缺失、结构错乱等问题。对此,提出一种自适应卷积约束与全局上下文推理的墓室壁画修复。方法基于端到端的编码器—解码器架构,首先设计多尺度增强卷积模块,从频域和空域联合分析图像特性来充分捕获全局结构和局部纹理;同时在修复路径中加入融合差分卷积的增强激活单元来引入边缘先验信息,提高模型的绘制精度。其次,考虑到纹理和结构在绘制过程中的模式差异,在编码器—解码器间设计基于注意力交互引导的多尺度特征聚合模块,来加强全局稀疏信息的表征能力和相关性,并自适应选择增强有效特征。此外,为了获得真实准确的结果,在特征传递过程中利用自动掩码更新迭代来预测复杂缺失信息,引导解码器精确绘制多样化的损伤区域。结果本文采用客观评价指标峰值信噪比(peak signal-to-noise ratio,PSNR)、结构相似性(structural similarity index,SSIM)和学习感知图像块相似度(learned perceptual image patch similarity,LPIPS)在章怀太子墓“马球图”数据集上进行3类模拟病害和真实病害修复实验,并与6种主流方法进行比较。实验结果表明,本文方法修复的壁画图像在主观视觉和客观评价上均有明显提升。相较于指标排名第2的模型,对于随机缺失区域的壁画修复,峰值信噪比和结构相似性的均值分别达到31.7602dB和0.9577,各指标的样本均值分别提升了2.3653 dB、0.0128和12.75%。结论本文提出的图像修复模型可以有效修复多种复杂病害,可为手工绘制专家的物理修复提供参考,进一步促进了数字文化遗产的Objective As an important cultural heritage of ancient civilization,murals have suffered over the years due to environmental factors such as humidity and ground settlement.This phenomenon has led to issues such as peeling,cracks,mud spots,and mildew,which seriously affect the sustainable development of mural preservation and hinder activities related to appreciation,cultural creativity,and cultural dissemination.Considering the influence of underground environmental factors,researchers often use block excavation methods to transfer and restore the murals.Traditionally,the restoration process requires professional restorers to manually redraw the murals,which demands a high level of skill and results in a lengthy and inefficient repair cycle.Therefore,in response to the complex semantic environment and the lack of diverse information,deep learning-based restoration methods have been gradually applied to the reconstruction of murals,providing scientific and technological protection for murals.However,most existing methods typically perform restoration in a single dimension or within a fixed area,which fails to fully capture sparse mural features and repair multiple complex diseases simultaneously.This phenomenon results in semantic inconsistencies or incoherent structural results.This paper proposes a tomb mural inpainting model with adaptive convolutional constraints and global context inference to solve the above problems.This model can repair various types of damage and diseases,producing a rich database of digital cultural heritage.Method Based on the end-to-end encoder-decoder architecture,the model first designs a multiscale enhanced convolution(MEConv)module in the encoder path for content constraints and extracts different features of the image from the frequency and spatial domains simultaneously to complement each other.The enhanced activation unit fused with differential convolution is also added to the repair path to introduce edge prior information,correcting the adaptive multiscale feature mapping,whi

关 键 词：壁画修复 多尺度增强卷积模块 多尺度特征聚合模块 增强激活单元 差分卷积 病害修复 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]