计算机科学与探索2026，Vol.20Issue(6)：1627-1636,10.DOI:10.3778/j.issn.1673-9418.2508077
室内环境下融合G-ICP与三维高斯溅射的视觉SLAM算法
Visual SLAM Algorithm Integrating G-ICP and 3D Gaussian Splatting for Indoor Environments
摘要
Abstract
To address the problem that traditional visual simultaneous localization and mapping(SLAM)algorithms in indoor environments are affected by highly reflective objects and low-texture regions,resulting in decreased localization accuracy and degraded mapping quality,a visual SLAM algorithm integrating 3D Gaussian splatting(3DGS)and general-ized iterative closest point(G-ICP)is proposed,named GICP-STAM.Firstly,3DGS and G-ICP algorithms are integrated for pose initialization.Secondly,keyframe selection is performed based on G-ICP registration results to remove keyframes with low information density.Finally,a λSSIM loss strategy is proposed for Gaussian pruning and densification to filter out abnormal map points and create new map points.Experimental validation is conducted using three public datasets of indoor environments.The experimental results show that,compared with the baseline algorithm SplaTAM,the absolute trajectory error root mean square error(ATE RMSE)is improved by 38%,11%,and 3%on the Replica,TUM-RGBD,and ScanNet datasets,respectively;the average peak signal-to-noise ratio(PSNR)on the Replica and ScanNet datasets is improved by 6%and 23%,respectively.The localization accuracy and mapping quality in indoor environments are significantly better than those of the baseline algorithm.关键词
室内环境/视觉即时定位与建图(SLAM)/三维高斯溅射(3DGS)/广义迭代最近点(G-ICP)Key words
indoor environments/visual simultaneous localization and mapping(SLAM)/3D Gaussian splatting(3DGS)/generalized iterative closest point(G-ICP)分类
信息技术与安全科学引用本文复制引用
张建树,张军..室内环境下融合G-ICP与三维高斯溅射的视觉SLAM算法[J].计算机科学与探索,2026,20(6):1627-1636,10.基金项目
国家自然科学基金(62371013) （62371013）
北京市属高等学校高水平科研创新团队建设支持计划项目(BPHR20220121). This work was supported by the National Natural Science Foundation of China(62371013),and the Beijing Municipal High-Level Research and Innovation Team Construction Support Program(BPHR20220121). （BPHR20220121）
