RGBD GS-ICP SLAM

TL;DR

This paper introduces a fast and accurate dense SLAM method combining G-ICP and 3D Gaussian Splatting, utilizing a single Gaussian map for tracking and mapping to improve efficiency and quality.

Contribution

It presents a novel dense SLAM approach that fuses G-ICP with 3D Gaussian Splatting, using a unified Gaussian map and covariance exchange for enhanced performance.

Findings

Achieves up to 107 FPS processing speed.

Demonstrates superior map reconstruction quality.

Reduces computational redundancy through covariance exchange.

Abstract

Simultaneous Localization and Mapping (SLAM) with dense representation plays a key role in robotics, Virtual Reality (VR), and Augmented Reality (AR) applications. Recent advancements in dense representation SLAM have highlighted the potential of leveraging neural scene representation and 3D Gaussian representation for high-fidelity spatial representation. In this paper, we propose a novel dense representation SLAM approach with a fusion of Generalized Iterative Closest Point (G-ICP) and 3D Gaussian Splatting (3DGS). In contrast to existing methods, we utilize a single Gaussian map for both tracking and mapping, resulting in mutual benefits. Through the exchange of covariances between tracking and mapping processes with scale alignment techniques, we minimize redundant computations and achieve an efficient system. Additionally, we enhance tracking accuracy and mapping quality through our keyframe selection methods. Experimental results demonstrate the effectiveness of our approach, showing an incredibly fast speed up to 107 FPS (for the entire system) and superior quality of the reconstructed map.