首个支持大场景的3D高斯SLAM框架，解决内存爆炸与位姿漂移问题。
VPGS-SLAM: Voxel-based Progressive 3D Gaussian SLAM in Large-Scale Scenes
- 基于体素分块的渐进式高斯映射，多子地图实现紧凑表征
- 在多个大场景数据集上实现亚厘米级精度，支持长序列运行
- 适合需要高精度定位的自动驾驶与机器人导航场景
3D高斯点阵最近在稠密视觉SLAM中表现出色。然而，现有基于3DGS的SLAM方法均局限于小房间场景，在大场景和长序列下易出现内存爆炸。为此，我们提出VPGS-SLAM，首个适用于室内外大场景的基于3DGS的RGBD SLAM框架。设计了一种新型体素分块的渐进式3D高斯建图方法，采用多个子地图实现大场景与长序列下的紧凑且精确的场景表示，可扩展至任意规模场景并提升鲁棒性（即使存在位姿漂移）。此外，提出2D-3D融合的相机跟踪方法，实现在室内外大场景中的稳定精准追踪；设计2D-3D高斯回环检测方法以消除位姿漂移；进一步提出在线蒸馏的子地图融合策略，实现回环检测时的大场景全局一致性。在多种室内外数据集上的实验验证了该框架的优越性与泛化能力。代码将开源于https://github.com/dtc111111/vpgs-slam。
原文摘要 · Abstract (English)
3D Gaussian Splatting has recently shown promising results in dense visual SLAM. However, existing 3DGS-based SLAM methods are all constrained to small-room scenarios and struggle with memory explosion in large-scale scenes and long sequences. To this end, we propose VPGS-SLAM, the first 3DGS-based large-scale RGBD SLAM framework for both indoor and outdoor scenarios. We design a novel voxel-based progressive 3D Gaussian mapping method with multiple submaps for compact and accurate scene representation in large-scale and long-sequence scenes. This allows us to scale up to arbitrary scenes and improves robustness (even under pose drifts). In addition, we propose a 2D-3D fusion camera tracking method to achieve robust and accurate camera tracking in both indoor and outdoor large-scale scenes. Furthermore, we design a 2D-3D Gaussian loop closure method to eliminate pose drift. We further propose a submap fusion method with online distillation to achieve global consistency in large-scale scenes when detecting a loop. Experiments on various indoor and outdoor datasets demonstrate the superiority and generalizability of the proposed framework. The code will be open source on https://github.com/dtc111111/vpgs-slam.
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。