西安工程大学学报2025，Vol.39Issue(2)：75-83,9.DOI:10.13338/j.issn.1674-649x.2025.02.009
基于LW-LoFTR的增强现实三维注册算法
Augmented reality 3D registration algorithm based on LW-LoFTR
摘要
Abstract
Three dimensional registration is a key step in implementing augmented reality(AR).In order to solve the problem of natural feature-based 3D registration algorithms being easily affected by the environ-ment,inaccurate registration results,and time-consuming when used in complex scenes,the LW-LoFTR(lightweight-LoFTR)algorithm was proposed to lightweight improve the model to meet the low latency re-quirements of AR.Firstly,depthwise separable convolution was used to reduce the number of model param-eters and inference time.Secondly,a lightweight global context module was added to improve the feature interaction capability of the model and compensate for the loss of accuracy after lightweighting.Finally,the matching relationship obtained by the LW-LoFTR algorithm was used for pose calculation,completing the optimization and improvement of 3D registration,and achieving high-performance AR effects.The experi-mental results show that the proposed LW-LoFTR algorithm achieves an average matching accuracy of 94.59%on the MegaDepth dataset.When the statistical error thresholds are 5°,10°,and 20°,the relative pose estimation AUC(area under curve)reaches 48.85,65.56 and 78.72,respectively.The number of model pa-rameters decreases by 43.97%,and the inference time decreases by 48.92%.It can achieve stable 3D regis-tration effects under changes in viewing angle,lighting,and occlusion.关键词
增强现实(AR)/三维注册/轻量化/图像匹配/深度学习Key words
augmented reality(AR)/3D registration/lightweight/image matching/deep learning分类
信息技术与安全科学引用本文复制引用
石虹,徐伟,刘少清..基于LW-LoFTR的增强现实三维注册算法[J].西安工程大学学报,2025,39(2):75-83,9.基金项目
安徽高校协同创新项目(GXXT-2022-003) （GXXT-2022-003）
合肥综合性国家科学中心能源研究院(安徽省能源实验室)项目(21KZS208) （安徽省能源实验室）
