高斯泼溅SLAM
Gaussian Splatting SLAM
AI总结：
该研究首次将3D Gaussian Splatting应用于单目SLAM，通过直接优化高斯实现鲁棒跟踪、引入几何正则化解歧义，构建的完整系统在新视角合成、轨迹估计及微小透明物体重建上达SOTA，且可扩展至RGB-D SLAM。
摘要：
我们首次将3D Gaussian Splatting应用于单目SLAM——这是视觉SLAM最基础也最具挑战性的设置。我们的方法以3fps的速度实时运行，仅使用高斯作为3D表示，统一了实现精准高效跟踪、建图与高质量渲染所需的表示形式。该方法专为具有挑战性的单目场景设计，当有外部深度传感器时，可无缝扩展到RGB-D SLAM。\n要从实时相机中连续高保真重建3D场景，需要多项创新。首先，原始3DGS算法依赖离线运动恢复结构（SfM）系统提供的精准位姿，为突破这一限制，我们通过对3D高斯进行直接优化，构建了适用于3DGS的相机跟踪方法，并证明该方法收敛域宽，可实现快速鲁棒的跟踪。其次，我们利用高斯的显式特性，引入几何验证与正则化，以处理增量式3D稠密重建中出现的歧义问题。最后，我们构建了一套完整的SLAM系统，该系统不仅在新视角合成与轨迹估计方面取得了当前最优结果，还能重建微小甚至透明的物体。
英文摘要：
We present the first application of 3D Gaussian Splatting in monocular SLAM, the most fundamental but the hardest setup for Visual SLAM. Our method, which runs live at 3fps, utilises Gaussians as the only 3D representation, unifying the required representation for accurate, efficient tracking, mapping, and high-quality rendering. Designed for challenging monocular settings, our approach is seamlessly extendable to RGB-D SLAM when an external depth sensor is available. Several innovations are required to continuously reconstruct 3D scenes with high fidelity from a live camera. First, to move beyond the original 3DGS algorithm, which requires accurate poses from an offline Structure from Motion (SfM) system, we formulate camera tracking for 3DGS using direct optimisation against the 3D Gaussians, and show that this enables fast and robust tracking with a wide basin of convergence. Second, by utilising the explicit nature of the Gaussians, we introduce geometric verification and regularisation to handle the ambiguities occurring in incremental 3D dense reconstruction. Finally, we introduce a full SLAM system which not only achieves state-of-the-art results in novel view synthesis and trajectory estimation but also reconstruction of tiny and even transparent objects.
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。
