发表机构
State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University; Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province（工业控制技术国家重点实验室，浙江大学控制科学与工程学院; 浙江省协同感知与自主无人系统重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出GeoGS-SLAM在线单目密集重建系统，结合3DGS地图表示与几何先验。利用前馈模型预测先验，通过采样扩展地图，粗到细优化姿态和地图，纳入回环检测与姿态图优化，实验表明其在质量、精度和实时性上优于现有方法。
AI 中文摘要
基于3D高斯点云（3DGS）的SLAM方法展现出了令人印象深刻的跟踪和映射性能，但通常需要来自外部深度传感器的额外几何信息。同时，最近利用预训练前馈模型的几何先验的SLAM系统能够进行实时密集重建，但在优化过程中常常丢弃原始RGB信息，从而降低整体重建质量。我们提出了GeoGS-SLAM，一种在线单目密集重建系统，它将基于3DGS的地图表示与学习到的几何先验相结合。给定未校准的RGB输入，我们首先使用前馈视觉几何模型来预测相机和场景先验。然后通过直接从RGB输入和几何先验中采样高斯基元来扩展高斯场景地图。相机姿态和场景地图通过粗到细的策略进行联合优化，该策略使光度和几何损失最小化。为确保全局一致性，我们进一步纳入在线回环检测和姿态图优化。在室内和室外基准上的大量实验表明，与现有方法相比，GeoGS-SLAM在保持在线实时性能的同时，实现了卓越的渲染质量和跟踪精度。项目页面：此https URL。
英文摘要
SLAM methods based on 3D Gaussian Splatting (3DGS) have demonstrated impressive tracking and mapping performance, but typically require additional geometric information from external depth sensors. Meanwhile, recent SLAM systems that leverage geometric priors from pre-trained feed-forward models enable real-time dense reconstruction, yet often discard original RGB information during optimization, thus degrading overall reconstruction quality. We present GeoGS-SLAM, an online monocular dense reconstruction system that combines the 3DGS-based map representation with learned geometric priors. Given uncalibrated RGB input, we first employ a feed-forward visual geometry model to predict camera and scene priors. The Gaussian scene map is then expanded by directly sampling Gaussian primitives from both RGB input and geometric priors. Camera poses and the scene map are jointly optimized through a coarse-to-fine strategy that minimizes both photometric and geometric losses. To ensure global consistency, we further incorporate online loop closure detection and pose graph optimization. Extensive experiments across indoor and outdoor benchmarks demonstrate that GeoGS-SLAM achieves superior rendering quality and tracking accuracy compared to state-of-the-art methods while maintaining online real-time performance. Project page: https://rlgao.github.io/geogs_slam.
