VPGS-SLAM: Voxel-based Progressive 3D Gaussian SLAM in Large-Scale Scenes

2025-05-25

AI Summary

Existing 3D Gaussian Splatting (3DGS)-based SLAM methods suffer from memory explosion in large-scale or long-sequence scenarios, limiting their applicability to massive indoor–outdoor environments. This paper proposes the first 3DGS-SLAM framework designed explicitly for large-scale scenes. Our method addresses key challenges through three core innovations: (1) voxelized progressive multi-submap Gaussian mapping to curb memory growth; (2) tightly coupled 2D–3D fusion camera tracking for enhanced pose robustness; and (3) loop closure detection leveraging joint feature points and Gaussian ellipsoids, combined with online knowledge distillation–driven submap fusion to ensure global consistency. Integrated with voxel hash indexing, RGB-D multimodal tracking, and joint optimization, our approach achieves state-of-the-art performance across multiple large-scale indoor–outdoor benchmarks—supporting arbitrary scene scales while maintaining real-time operation, low drift, and high-fidelity reconstruction.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

3D Gaussian Splatting has recently shown promising results in dense visual SLAM. However, existing 3DGS-based SLAM methods are all constrained to small-room scenarios and struggle with memory explosion in large-scale scenes and long sequences. To this end, we propose VPGS-SLAM, the first 3DGS-based large-scale RGBD SLAM framework for both indoor and outdoor scenarios. We design a novel voxel-based progressive 3D Gaussian mapping method with multiple submaps for compact and accurate scene representation in large-scale and long-sequence scenes. This allows us to scale up to arbitrary scenes and improves robustness (even under pose drifts). In addition, we propose a 2D-3D fusion camera tracking method to achieve robust and accurate camera tracking in both indoor and outdoor large-scale scenes. Furthermore, we design a 2D-3D Gaussian loop closure method to eliminate pose drift. We further propose a submap fusion method with online distillation to achieve global consistency in large-scale scenes when detecting a loop. Experiments on various indoor and outdoor datasets demonstrate the superiority and generalizability of the proposed framework. The code will be open source on https://github.com/dtc111111/vpgs-slam.

Problem

• Addresses memory explosion in large-scale 3D Gaussian SLAM
• Enables robust indoor/outdoor mapping via voxel-based progressive submaps
• Reduces pose drift with 2D-3D fusion tracking and loop closure

Innovation

• Voxel-based progressive 3D Gaussian mapping
• 2D-3D fusion camera tracking method
• Submap fusion with online distillation