CaRtGS: Computational Alignment for Real-Time Gaussian Splatting SLAM

TL;DR

CaRtGS is a novel SLAM method that improves real-time, photorealistic scene reconstruction by enhancing Gaussian Splatting techniques, leading to higher quality and efficiency in dynamic environments.

Contribution

It introduces an adaptive alignment strategy for Gaussian Splatting SLAM, significantly improving optimization and densification for real-time photorealistic scene reconstruction.

Findings

Achieves high-fidelity rendering with fewer Gaussian primitives.

Demonstrates superior performance on multiple datasets.

Advances real-time photorealistic dense scene reconstruction.

Abstract

Simultaneous Localization and Mapping (SLAM) is pivotal in robotics, with photorealistic scene reconstruction emerging as a key challenge. To address this, we introduce Computational Alignment for Real-Time Gaussian Splatting SLAM (CaRtGS), a novel method enhancing the efficiency and quality of photorealistic scene reconstruction in real-time environments. Leveraging 3D Gaussian Splatting (3DGS), CaRtGS achieves superior rendering quality and processing speed, which is crucial for scene photorealistic reconstruction. Our approach tackles computational misalignment in Gaussian Splatting SLAM (GS-SLAM) through an adaptive strategy that enhances optimization iterations, addresses long-tail optimization, and refines densification. Experiments on Replica, TUM-RGBD, and VECtor datasets demonstrate CaRtGS's effectiveness in achieving high-fidelity rendering with fewer Gaussian primitives. This work propels SLAM towards real-time, photorealistic dense rendering, significantly advancing photorealistic scene representation. For the benefit of the research community, we release the code and accompanying videos on our project website: https://dapengfeng.github.io/cartgs.