Simultaneous localization and mapping is essential for position tracking and
scene understanding. 3D Gaussian-based map representations enable
photorealistic reconstruction and real-time rendering of scenes using multiple
posed cameras. We show for the first time that using 3D Gaussians for map
representation with unposed camera images and inertial measurements can enable
accurate SLAM. Our method, MM3DGS, addresses the limitations of prior neural
radiance field-based representations by enabling faster rendering, scale
awareness, and improved trajectory tracking. Our framework enables
keyframe-based mapping and tracking utilizing loss functions that incorporate
relative pose transformations from pre-integrated inertial measurements, depth
estimates, and measures of photometric rendering quality. We also release a
multi-modal dataset, UT-MM, collected from a mobile robot equipped with a
camera and an inertial measurement unit. Experimental evaluation on several
scenes from the dataset shows that MM3DGS achieves 3x improvement in tracking
and 5% improvement in photometric rendering quality compared to the current
3DGS SLAM state-of-the-art, while allowing real-time rendering of a
high-resolution dense 3D map. Project Webpage:
this https URL

使用 3D 高斯地图表示方法，并结合未放置相机图像和惯性测量数据，能够实现准确的同步定位与映射（SLAM），并解决了神经辐射场表示方法的局限性，实现了更快的渲染、尺度感知和轨迹跟踪。同时，作者提供了 UT-MM 多模态数据集，经实验评估表明 MM3DGS 相比现有 3DGS SLAM 技术可以实现 3 倍的跟踪改进和 5% 的光度渲染质量提升，并且能够实现高分辨率稠密 3D 地图的实时渲染。