SING3R-SLAM：基于子地图的室内单目高斯SLAM与3D重建先验
SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priors
AI总结：
本文提出SING3R-SLAM，通过全局一致的高斯地图和子地图级全局对齐，实现高效的室内单目SLAM与3D重建，实验显示其在姿态估计、3D重建和视图渲染方面性能优异。
摘要：
近期密集3D重建的进展展示了在准确捕捉局部几何方面的强大能力。然而，将其扩展到需要增量全局重建的SLAM系统仍具挑战性。没有显式建模全局几何一致性，现有方法常导致累积漂移、尺度不一致和局部几何次优。为解决这些问题，我们提出了SING3R-SLAM，一种全局一致的高斯基单目室内SLAM框架。我们的方法通过全局高斯地图表示场景，作为持久且可微的记忆体，结合子地图级全局对齐进行局部几何重建，并利用全局地图的一致性进一步细化局部几何。这种设计实现了多种下游应用的高效且多功能的3D映射。广泛实验表明，SING3R-SLAM在姿态估计、3D重建和新视图渲染方面实现了最先进的性能。它通过超过10%的精度提升，产生更精细和详细的几何结构，并在真实世界数据集上保持紧凑且内存高效的全局表示。
英文摘要：
Recent advances in dense 3D reconstruction have demonstrated strong capability in accurately capturing local geometry. However, extending these methods to incremental global reconstruction, as required in SLAM systems, remains challenging. Without explicit modeling of global geometric consistency, existing approaches often suffer from accumulated drift, scale inconsistency, and suboptimal local geometry. To address these issues, we propose SING3R-SLAM, a globally consistent Gaussian-based monocular indoor SLAM framework. Our approach represents the scene with a Global Gaussian Map that serves as a persistent, differentiable memory, incorporates local geometric reconstruction via submap-level global alignment, and leverages global map's consistency to further refine local geometry. This design enables efficient and versatile 3D mapping for multiple downstream applications. Extensive experiments show that SING3R-SLAM achieves state-of-the-art performance in pose estimation, 3D reconstruction, and novel view rendering. It improves pose accuracy by over 10%, produces finer and more detailed geometry, and maintains a compact and memory-efficient global representation on real-world datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
