spla-tam.github.io - SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM

Description: SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM

tracking (1539) mapping (987) slam (187) dense (50) pose estimation (5) 3d gaussian splatting (5) rgb-d (1) splats (1) gaussians (1)

Example domain paragraphs

Dense simultaneous localization and mapping (SLAM) is pivotal for embodied scene understanding. Recent work has shown that 3D Gaussians enable high-quality reconstruction and real-time rendering of scenes using multiple posed cameras. In this light, we show for the first time that representing a scene by a 3D Gaussian Splatting radiance field can enable dense SLAM using a single unposed monocular RGB-D camera. Our method, SplaTAM, addresses the limitations of prior radiance field-based representations, incl

If you use the source code of this website, please also link back to the Nerfies source code in your footer.

Dense simultaneous localization and mapping (SLAM) is crucial for robotics and augmented reality applications. However, current methods are often hampered by the non-volumetric or implicit way they represent a scene. This work introduces SplaTAM, an approach that, for the first time, leverages explicit volumetric representations, i.e., 3D Gaussians, to enable high-fidelity reconstruction from a single unposed RGB-D camera, surpassing the capabilities of existing methods. SplaTAM employs a simple online trac

Links to spla-tam.github.io (4)

gengshan-y.github.io Gengshan Yang | 杨庚山
nik-v9.github.io Nikhil Varma Keetha
jaykarhade.github.io Jay Karhade
3dvisionreadinggroup.github.io 3D Vision Reading Group | 3D Vision Reading Group webpage.