RGBDS-SLAM: A RGB-D Semantic Dense SLAM Based on 3D Multi Level Pyramid Gaussian Splatting

TL;DR

RGBDS-SLAM introduces a novel multi-level pyramid Gaussian splatting approach for RGB-D semantic dense SLAM, significantly improving scene reconstruction quality and consistency across RGB, depth, and semantic maps.

Contribution

It proposes a multi-level pyramid Gaussian splatting method and a multi-features optimization mechanism for enhanced dense scene reconstruction.

Findings

Outperforms state-of-the-art methods on Replica and ScanNet datasets.

Achieves high-quality, consistent RGB, depth, and semantic reconstructions.

Demonstrates effectiveness through extensive experiments and ablation studies.

Abstract

High-quality reconstruction is crucial for dense SLAM. Recent popular approaches utilize 3D Gaussian Splatting (3D GS) techniques for RGB, depth, and semantic reconstruction of scenes. However, these methods often overlook issues of detail and consistency in different parts of the scene. To address this, we propose RGBDS-SLAM, a RGB-D semantic dense SLAM system based on 3D multi-level pyramid gaussian splatting, which enables high-quality dense reconstruction of scene RGB, depth, and semantics.In this system, we introduce a 3D multi-level pyramid gaussian splatting method that restores scene details by extracting multi-level image pyramids for gaussian splatting training, ensuring consistency in RGB, depth, and semantic reconstructions. Additionally, we design a tightly-coupled multi-features reconstruction optimization mechanism, allowing the reconstruction accuracy of RGB, depth, and semantic maps to mutually enhance each other during the rendering optimization process. Extensive quantitative, qualitative, and ablation experiments on the Replica and ScanNet public datasets demonstrate that our proposed method outperforms current state-of-the-art methods. The open-source code will be available at: https://github.com/zhenzhongcao/RGBDS-SLAM.