实时单目稠密建图，用双向耦合提升精度与速度
GSO-SLAM: Bidirectionally Coupled Gaussian Splatting and Direct Visual Odometry
- VO与高斯点云双向耦合，联合优化无额外开销
- 重建几何与光照保真度达顶尖水平，跟踪更准
- 无需启发式初始化，直接从视觉里程计生成初始点云
我们提出 GSO-SLAM，一种基于高斯场景表示的实时单目稠密 SLAM 系统。与现有方法中统一建模导致计算开销大，或松散集成追踪框架引入冗余不同，本方法在期望最大化（EM）框架下实现视觉里程计（VO）与高斯点云（GS）的双向耦合。该设计使 VO 的半稠密深度估计与 GS 表示可同时优化，且不增加额外计算负担。此外，我们提出高斯点云初始化（Gaussian Splat Initialization），利用图像信息、关键帧位姿及像素对应关系，快速生成接近最终结果的高斯场景，避免依赖启发式方法。大量实验验证了本方法的有效性：系统可实时运行，并在重建场景的几何/光度保真度和跟踪精度上达到当前最优水平。
原文摘要 · Abstract (English)
We propose GSO-SLAM, a real-time monocular dense SLAM system that leverages Gaussian scene representation. Unlike existing methods that couple tracking and mapping with a unified scene, incurring computational costs, or loosely integrate them with well-structured tracking frameworks, introducing redundancies, our method bidirectionally couples Visual Odometry (VO) and Gaussian Splatting (GS). Specifically, our approach formulates joint optimization within an Expectation-Maximization (EM) framework, enabling the simultaneous refinement of VO-derived semi-dense depth estimates and the GS representation without additional computational overhead. Moreover, we present Gaussian Splat Initialization, which utilizes image information, keyframe poses, and pixel associations from VO to produce close approximations to the final Gaussian scene, thereby eliminating the need for heuristic methods. Through extensive experiments, we validate the effectiveness of our method, showing that it not only operates in real time but also achieves state-of-the-art geometric/photometric fidelity of the reconstructed scene and tracking accuracy.
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。