TVG-SLAM：基于三视图几何约束的鲁棒高斯泼溅SLAM
TVG-SLAM: Robust Gaussian Splatting SLAM with Tri-view Geometric Constraints
AI总结：
提出TVG-SLAM，一种利用三视图几何范式结合混合几何约束与概率初始化策略的纯RGB 3DGS SLAM系统，有效解决了户外环境下的追踪鲁棒性问题，显著降低了轨迹误差并提升了渲染质量。
摘要：
3D高斯泼溅（3DGS）的最新进展使得纯RGB SLAM系统能够实现高保真的场景表示。然而，现有系统严重依赖光度渲染损失进行相机追踪，这削弱了它们的鲁棒性，特别是在具有严重视角和光照变化的无界户外环境中。为了应对这些挑战，我们提出了TVG-SLAM，这是一个鲁棒的纯RGB 3DGS SLAM系统，它利用一种新颖的三视图几何范式来确保一致的追踪和高质量的建图。我们引入了一个密集三视图匹配模块，将可靠的成对对应关系聚合为一致的三视图匹配，从而在帧之间形成鲁棒的几何约束。对于追踪，我们提出了混合几何约束，利用三视图匹配构建与光度损失互补的几何线索，确保在剧烈视角偏移和光照变化下仍能进行准确稳定的位姿估计。对于建图，我们提出了一种新的概率初始化策略，将来自三视图对应关系的几何不确定性编码到新初始化的高斯分布中。此外，我们设计了渲染信任动态衰减机制，以减轻由建图延迟引起的追踪漂移。在多个公开户外数据集上的实验表明，我们的TVG-SLAM优于先前的纯RGB 3DGS SLAM系统。值得注意的是，在最具挑战性的数据集中，我们的方法提高了追踪鲁棒性，将平均绝对轨迹误差（ATE）降低了69.0%，同时实现了最先进的渲染质量。我们方法的实现将作为开源发布。
英文摘要：
Recent advances in 3D Gaussian Splatting (3DGS) have enabled RGB-only SLAM systems to achieve high-fidelity scene representation. However, the heavy reliance of existing systems on photometric rendering loss for camera tracking undermines their robustness, especially in unbounded outdoor environments with severe viewpoint and illumination changes. To address these challenges, we propose TVG-SLAM, a robust RGB-only 3DGS SLAM system that leverages a novel tri-view geometry paradigm to ensure consistent tracking and high-quality mapping. We introduce a dense tri-view matching module that aggregates reliable pairwise correspondences into consistent tri-view matches, forming robust geometric constraints across frames. For tracking, we propose Hybrid Geometric Constraints, which leverage tri-view matches to construct complementary geometric cues alongside photometric loss, ensuring accurate and stable pose estimation even under drastic viewpoint shifts and lighting variations. For mapping, we propose a new probabilistic initialization strategy that encodes geometric uncertainty from tri-view correspondences into newly initialized Gaussians. Additionally, we design a Dynamic Attenuation of Rendering Trust mechanism to mitigate tracking drift caused by mapping latency. Experiments on multiple public outdoor datasets show that our TVG-SLAM outperforms prior RGB-only 3DGS-based SLAM systems. Notably, in the most challenging dataset, our method improves tracking robustness, reducing the average Absolute Trajectory Error (ATE) by 69.0\% while achieving state-of-the-art rendering quality. The implementation of our method will be released as open-source.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
