针对3D高斯溅射SLAM，提出几何感知的增量映射方法。
Geometry-Aware Online Mapping for 3D Gaussian Splatting SLAM
- 基于透明度保持的密度增长策略
- 利用深度与内参实现相机感知初始化
- 误差引导新增高残差区域的点云
近期3D高斯溅射（3DGS）实现了高效逼真的视图合成，正被快速应用于实时同步定位与建图（SLAM）系统。在这些系统中，需在跟踪过程中实时增量式扩展和优化高斯地图，因此初始化与密度控制直接决定有限计算资源和迭代次数的分配。这与可进行长时间优化的离线3DGS重建形成对比。然而，多数3DGS-SLAM系统沿用离线重建的启发式策略，在在线SLAM严格的每帧优化预算和增量地图增长下易失效。本文在解耦的3DGS-SLAM框架下重新审视这些启发式方法，提出三种在映射线程中运行的几何感知方法：透明度保持的密度增长、基于深度与内参的相机感知尺度初始化，以及聚焦于高残差区域的误差引导密度增长。实验表明，渲染质量显著提升且开销可忽略，凸显了在线SLAM中光度残差与位姿不确定性之间的耦合关系。代码将开源以促进社区发展与可复现性。
原文摘要 · Abstract (English)
Recent 3D Gaussian Splatting (3DGS) has enabled efficient photorealistic view synthesis and is rapidly being adopted in simultaneous localization and mapping (SLAM) systems for online mapping. In these systems, a Gaussian map must be expanded and refined incrementally while tracking runs in real time, so initialization and density control directly determine where limited computation and iterations are spent. This contrasts with offline 3DGS reconstruction, where such heuristics can be amortized over long optimization schedules. However, most 3DGS-SLAM pipelines inherit initialization and density-control heuristics from offline reconstruction, which can become brittle under the strict per-keyframe optimization budgets and incremental map growth of online SLAM. In this work, we revisit these heuristics in a decoupled 3DGS-SLAM setting and propose three geometry-aware methods that operate in the mapping thread: transmittance-preserving densification, camera-aware scale initialization from depth and intrinsics, and error-guided densification that focuses new primitives on high-residual regions. Our results show consistent improvements in rendering quality with negligible overhead, highlighting the coupling between photometric residuals and pose uncertainty in online SLAM. We will open-source our code to the community to foster growth and validate reproducibility.
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。