鲁棒且高效的单目3D高斯SLAM用于千米级室外场景
Robust and Efficient Monocular 3D Gaussian SLAM for Kilometer-Scale Outdoor Scenes
AI总结：
提出KiloGS-SLAM系统，通过运动自适应混合跟踪模块和生命周期管理的高斯映射策略，解决千米级室外场景中单目3DGS-SLAM的长期跟踪漂移和内存开销问题，实现高精度跟踪与渲染。
摘要：
将单目3D高斯泼溅（3DGS）SLAM扩展到千米级室外环境面临两个紧密耦合的挑战：脆弱的长期位姿跟踪和大规模建图过程中的过度内存开销。本文提出KiloGS-SLAM，一个高效且鲁棒的单目3DGS-SLAM系统，联合解决这两个瓶颈。由于高保真场景重建根本上依赖于无漂移的相机位姿，我们首先引入一个运动自适应混合跟踪模块。该模块具有条件触发的三级求解流水线，动态切换本质矩阵和PnP模型以处理几何退化。还可以按需激活基础模型以将轨迹从灾难性漂移中拯救出来。为确保系统能够维持这些长轨迹而不耗尽内存，我们随后设计了一个生命周期管理的高斯映射策略。通过将概率初始化与基于块的多视图稠密化和剪枝相结合，这种全流水线优化有效减少了图元冗余，同时保留了高频细节。总之，鲁棒跟踪保证了精确建图所需的几何基础，而内存高效的生命周期管理映射则实现了大规模操作。在三个具有挑战性的室外数据集上的大量实验表明，我们的方法达到了最先进的跟踪精度和渲染质量，成功地在单个GPU上扩展到超过10,000帧的序列。
英文摘要：
Scaling monocular 3D Gaussian Splatting (3DGS) SLAM to kilometer-level outdoor environments poses two tightly coupled challenges: fragile long-term pose tracking and excessive memory overhead during large-scale mapping. In this paper, we propose KiloGS-SLAM, a highly efficient and robust monocular 3DGS-SLAM system that jointly addresses both bottlenecks. Since high-fidelity scene reconstruction fundamentally relies on drift-free camera poses, we first introduce a motion-adaptive hybrid tracking module. This module features a condition-triggered three-tier solving pipeline. It dynamically switches between Essential matrix and PnP models to handle geometric degeneracies. An on-demand foundation model can also be activated to rescue the trajectory from catastrophic drift. To ensure the system can sustain these long trajectories without memory exhaustion, we subsequently design a lifecycle-managed Gaussian mapping strategy. By integrating probabilistic initialization with chunk-based multi-view densification and pruning, this full-pipeline optimization effectively reduces primitive redundancy while preserving high-frequency details. Together, the robust tracking guarantees the geometric foundation required for accurate mapping, while the memory-efficient lifecycle-managed mapping enables large-scale operation. Extensive experiments across three challenging outdoor datasets demonstrate that our approach achieves state-of-the-art tracking accuracy and rendering quality, successfully scaling to sequences of over 10,000 frames on a single GPU.
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。
