西安工程大学学报2025，Vol.39Issue(2)：102-108,7.DOI:10.13338/j.issn.1674-649x.2025.02.012
文物三维重建中应用改进U2-Net的环境噪声处理方法
Environmental noise processing method based on improved U2-Net in 3D reconstruction of cultural relics
摘要
Abstract
When collecting image data for 3D reconstruction at real scenes,it is often difficult to avoid environmental noise interference,which affects the quality and accuracy of modeling.There-fore,it is necessary to process the relevant noise to accurately extract the main features of cultural relics.To address this issue,a multi-view 3D reconstruction analysis of bronze sculptures on cam-pus was conducted based on an improved U2-Net neural network.Firstly,an attention mechanism was added to the U2-Net neural network to improve the segmentation accuracy of the network for cultural relics,thereby obtaining images that only contain the features of cultural relics,and seg-menting cultural relics in three different environments.Finally,the monocular multi-view 3D re-construction method was used to model the preprocessed images.The experimental results show that the improved U2-Net neural network has higher segmentation accuracy for the main features of cultural relics and is suitable for processing diverse environmental noise.The processed images reduce the reprojection error by about 25%and the root mean square projection error by 2/3 dur-ing the 3D modeling process.The modeling time is reduced by a total of 25%.关键词
文物数字化/三维重建/图像去噪/U2-Net/多视角三维重建Key words
digitalization of cultural relics/3D reconstruction/image denoising/U2-Net/multi-view 3D reconstruction分类
计算机与自动化引用本文复制引用
杨鹏程,王嘉豪,朱婧怡,崔嘉宝..文物三维重建中应用改进U2-Net的环境噪声处理方法[J].西安工程大学学报,2025,39(2):102-108,7.基金项目
陕西省科技厅自然科学基础研究计划-面上项目(2022JM-219) （2022JM-219）
