湖南大学学报（自然科学版）2025，Vol.52Issue(4)：1-15,15.DOI:10.16339/j.cnki.hdxbzkb.2025261
双向自回归Transformer与快速傅里叶卷积增强的壁画修复
Bidirectional Autoregressive Transformer and Fast Fourier Convolution Enhanced Mural Inpainting
摘要
Abstract
Aiming at the lack of global semantic consistency constraints and insufficient acquisition of local features of the current deep learning algorithms in the process of image restoration of broken murals,resulting in the restored murals being prone to boundary effects and blurring of details,this paper proposes a bidirectional autoregressive Transformer with fast Fourier convolutional enhancement of murals restoration method.First,a global semantic feature repair module based on the Transformer structure is designed,and an improved multi-head attention global semantic mural repair module is proposed using the bidirectional autoregressive mechanism with masked language modeling(MLM)to improve the repair capability of global semantic features.Then,a global semantic enhancement module consisting of gated convolution and a residual module is constructed to enhance the global semantic consistency constraint.Finally,the local detail repair module is designed,which adopts large kernel attention(LKA)and fast Fourier convolution(FFC)to improve the ability of capturing detailed features while reducing the loss of local detail information,so as to enhance the consistency of the local and overall features of the repaired murals.The experimental results of the digital restoration of real Dunhuang murals show that the proposed algorithm can effectively restore the structure and texture of the murals,and the subjective visual effect and objective evaluation indexes are better than the comparative algorithms.关键词
壁画修复/双向自回归Transformer/掩码语言模型/快速傅里叶卷积/语义增强Key words
mural inpainting/bidirectional autoregressive Transformer/masked language modeling/fast Fourier convolution/semantic enhancement分类
计算机与自动化引用本文复制引用
陈永,张世龙,杜婉君..双向自回归Transformer与快速傅里叶卷积增强的壁画修复[J].湖南大学学报（自然科学版）,2025,52(4):1-15,15.基金项目
教育部人文社会科学研究青年基金资助项目(19YJC760012),Humanities and Social Sciences Youth Foundation of Ministry of Education(19YJC760012) （19YJC760012）
兰州交通大学基础研究拔尖人才项目(2023JC36),Lanzhou Jiaotong University Basic Top-Notch Personnel Project(2023JC36) （2023JC36）
兰州交通大学重点研发项目(ZDYF2304),Key Research and Development Project of Lanzhou Jiaotong University(ZDYF2304) （ZDYF2304）
