发表机构
University of Arkansas; VinUniversity（阿肯色大学; VinUniversity）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对现有3D高斯溅射SLAM流水线的启发式方法在在线场景下的脆弱问题，提出三种几何感知建图方法，实现渲染质量提升且开销可忽略，并将开源代码。
AI 中文摘要
近期的3D高斯溅射（3DGS）技术已能实现高效的照片级真实感视图合成，并正快速被应用于同步定位与建图（SLAM）系统以开展在线建图。在这类系统中，高斯地图必须在实时跟踪运行的同时逐步扩展与优化，因此初始化和密度控制直接决定了有限的计算资源与迭代次数的分配，这与离线3DGS重建形成鲜明对比——离线重建中这类启发式方法可在长优化周期内摊销成本。然而，多数3DGS-SLAM流水线继承了离线重建的初始化与密度控制启发式方法，在在线SLAM严格的关键帧优化预算和增量地图增长的约束下，这类方法会变得脆弱。本研究在解耦的3DGS-SLAM场景中重新审视这些启发式方法，并在建图线程中提出三种几何感知方法：保持透射率的密集化、基于深度与内参的相机感知尺度初始化，以及将新图元聚焦于高残差区域的误差引导密集化。实验结果表明，这些方法在渲染质量上取得了持续提升，且开销可忽略不计，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。我们将向社区开源代码，以推动领域发展并验证可复现性。
英文摘要
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.
Journal refIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)
