单目相机下用期望最大化稳定点云，实现高精度建图与分割。
MonoEM-GS: Monocular Expectation-Maximization Gaussian Splatting SLAM
- 结合高斯点云与EM算法，统一多视角几何信息
- 在7-Scenes等数据集上定位误差低于0.35m，优于最新方法
- 支持直接在地图上做开放集分割，适合机器人导航场景
前馈几何基础模型可从RGB流中直接推断稠密点云和相机运动，为单目SLAM提供先验。然而其预测常具视角依赖性且噪声大：几何表现随视角变化，局部度量属性在帧间可能漂移。本文提出MonoEM-GS，一种将此类几何预测融入全局高斯点云表示的单目建图流程，显式解决上述不一致性。该方法将高斯点云与期望-最大化（EM）框架结合以稳定几何结构，并采用基于ICP的对齐方式实现单目位姿估计。此外，MonoEM-GS以多模态特征参数化高斯点，支持在重建地图上直接进行开放集分割及其他下游任务。我们在7-Scenes、TUM RGB-D和Replica数据集上评估了该方法，并与近期基线进行对比。
原文摘要 · Abstract (English)
Feed-forward geometric foundation models can infer dense point clouds and camera motion directly from RGB streams, providing priors for monocular SLAM. However, their predictions are often view-dependent and noisy: geometry can vary across viewpoints and under image transformations, and local metric properties may drift between frames. We present MonoEM-GS, a monocular mapping pipeline that integrates such geometric predictions into a global Gaussian Splatting representation while explicitly addressing these inconsistencies. MonoEM-GS couples Gaussian Splatting with an Expectation--Maximization formulation to stabilize geometry, and employs ICP-based alignment for monocular pose estimation. Beyond geometry, MonoEM-GS parameterizes Gaussians with multi-modal features, enabling in-place open-set segmentation and other downstream queries directly on the reconstructed map. We evaluate MonoEM-GS on 7-Scenes, TUM RGB-D and Replica, and compare against recent baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。