diff --git a/assets/SplaTAM.pdf b/assets/SplaTAM.pdf index 58c0ddf..03dd411 100644 Binary files a/assets/SplaTAM.pdf and b/assets/SplaTAM.pdf differ diff --git a/index.html b/index.html index f42c70e..99039b3 100644 --- a/index.html +++ b/index.html @@ -72,7 +72,8 @@

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

-
+

CVPR 2024

+
Nikhil Keetha1, @@ -237,12 +238,13 @@

Abstract

- 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, including fast rendering and optimization, the ability to determine if areas have been previously mapped, and structured map expansion by adding more Gaussians. - In particular, we employ an online tracking and mapping pipeline while tailoring it to specifically use an underlying Gaussian representation and silhouette-guided optimization via differentiable rendering. - Extensive experiments on simulated and real-world data show that SplaTAM achieves up to 2 X state-of-the-art performance in camera pose estimation, map construction, and novel-view synthesis, demonstrating its superiority over existing approaches. + 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 tracking and mapping system tailored to the underlying Gaussian representation. + It utilizes a silhouette mask to elegantly capture the presence of scene density. + This combination enables several benefits over prior representations, including fast rendering and dense optimization, quickly determining if areas have been previously mapped, and structured map expansion by adding more Gaussians. + Extensive experiments show that SplaTAM achieves up to 2x superior performance in camera pose estimation, map construction, and novel-view synthesis over existing methods, paving the way for more immersive high-fidelity SLAM applications.

@@ -611,6 +613,40 @@

Replica R0

+
+
+ +
+
+

Concurrent work

+ +
+

+ Given the fast pace of research these days, five concurrent SLAM papers using 3D Gaussians as the underlying representation showed up on arXiv. Surprisingly, each one had a unique way to do SLAM with 3D Gaussians. +

+

+ GS-SLAM does coarse to fine camera tracking based on sparse selection of Gaussians. +

+

+ Gaussian Splatting SLAM does monocular SLAM, where densification is performed using depth statistics. +

+

+ Photo-SLAM couples ORB-SLAM3 based camera tracking with 3DGS based mapping. +

+

+ COLMAP-Free 3DGS uses monocular depth estimation with 3DGS. +

+

+ Gaussian-SLAM couples DROID-SLAM based camera tracking with active & inactive 3DGS sub-maps. +

+
+
+
+ + +
+
+