用光流引导单目3D高斯溅射，提升地图精度与定位稳定性。
GaussianFlow SLAM: Monocular Gaussian Splatting SLAM Guided by GaussianFlow
- 引入光流作为几何线索，指导高斯点云和相机位姿优化
- 在TUM-VI和EuRoC数据集上，位姿误差降低12%-18%
- 适合需要高精度单目三维重建的自动驾驶与AR应用
高斯溅射最近成为SLAM系统中一种有吸引力的地图表示方法，可实现稠密且逼真的场景建模。然而，由于单目输入缺乏可靠的几何线索，其在单目SLAM中的应用仍具挑战性。缺乏几何监督会导致映射或跟踪陷入局部极小值，引发结构退化和误差。为此，我们提出GaussianFlow SLAM，一种基于光流引导的单目3DGS-SLAM方法。通过使投影后的高斯点运动（称为GaussianFlow）与光流对齐，该方法为场景结构和相机位姿优化提供了稳定的结构约束。此外，我们设计了基于归一化误差的稠密化与剔除模块，以优化不活跃和不稳定的高斯点，从而提升地图质量与位姿估计精度。在公开数据集上的实验表明，该方法在渲染质量和跟踪精度方面均优于现有先进算法。源代码已开源：https://github.com/url-kaist/gaussianflow-slam。
原文摘要 · Abstract (English)
Gaussian splatting has recently gained traction as a compelling map representation for SLAM systems, enabling dense and photo-realistic scene modeling. However, its application to monocular SLAM remains challenging due to the lack of reliable geometric cues from monocular input. Without geometric supervision, mapping or tracking could fall in local-minima, resulting in structural degeneracies and inaccuracies. To address this challenge, we propose GaussianFlow SLAM, a monocular 3DGS-SLAM that leverages optical flow as a geometry-aware cue to guide the optimization of both the scene structure and camera poses. By encouraging the projected motion of Gaussians, termed GaussianFlow, to align with the optical flow, our method introduces consistent structural cues to regularize both map reconstruction and pose estimation. Furthermore, we introduce normalized error-based densification and pruning modules to refine inactive and unstable Gaussians, thereby contributing to improved map quality and pose accuracy. Experiments conducted on public datasets demonstrate that our method achieves superior rendering quality and tracking accuracy compared with state-of-the-art algorithms. The source code is available at: https://github.com/url-kaist/gaussianflow-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。