Towards Next-Generation SLAM: A Survey on 3DGS-SLAM Focusing on Performance, Robustness, and Future Directions

TL;DR

This paper surveys the integration of 3D Gaussian Splatting with SLAM, focusing on achieving high-fidelity, real-time mapping. It organizes advances along four performance dimensions—rendering quality, tracking accuracy, reconstruction speed, and memory consumption—and analyzes robustness to motion blur and dynamic scenes. The authors provide a taxonomy of rendering-quality improvements, tracking optimization strategies, and memory-management techniques, supported by comparative insights on public benchmarks. They also outline future directions, including event-camera fusion, physics-aware modeling, and incorporation of large vision models, to guide the development of next-generation SLAM systems.

Abstract

Traditional Simultaneous Localization and Mapping (SLAM) systems often face limitations including coarse rendering quality, insufficient recovery of scene details, and poor robustness in dynamic environments. 3D Gaussian Splatting (3DGS), with its efficient explicit representation and high-quality rendering capabilities, offers a new reconstruction paradigm for SLAM. This survey comprehensively reviews key technical approaches for integrating 3DGS with SLAM. We analyze performance optimization of representative methods across four critical dimensions: rendering quality, tracking accuracy, reconstruction speed, and memory consumption, delving into their design principles and breakthroughs. Furthermore, we examine methods for enhancing the robustness of 3DGS-SLAM in complex environments such as motion blur and dynamic environments. Finally, we discuss future challenges and development trends in this area. This survey aims to provide a technical reference for researchers and foster the development of next-generation SLAM systems characterized by high fidelity, efficiency, and robustness.

Figures (10)

• Figure 1: Typical SLAM map representations and evolution of SLAM. The upper subfigures display diverse scene representations enabled by various SLAM approaches, highlighting the transition from simple geometric reconstructions to rich, visually realistic scene models. The lower panel presents the evolutionary stages of SLAM: starting from early probabilistic filters, through keyframe and feature-based enhancements, to the integration of deep learning and semantic reasoning, the recent adoption of NeRF, and finally the latest 3DGS approaches which are the focus of this survey.
• Figure 2: Overall structure of the article.
• Figure 3: General pipeline of 3D Gaussian Splatting. Initialized from sparse points, the method renders views via differentiable rasterization and iteratively refines the geometry through adaptive optimization.
• Figure 4: General Pipeline of 3DGS-SLAM. Taking frames as input, the system performs tracking to estimate poses and select keyframes. The mapping stage updates the scene, followed by loop closure and optimization to ensure global consistency.
• Figure 5: Summary of rendering quality optimization methods. We categorize representative approaches into five strategies: 1) Hybrid Representations: combining explicit Gaussians with implicit priors for robust initialization; 2) Vision-Guided Perception: exploiting visual residuals and structural cues for primitive densification; 3) Depth-Guided Optimization: enhancing geometric accuracy via MVS or multi-source depth fusion; 4) Progressive Training: utilizing pyramid-based mechanisms for coarse-to-fine refinement; and 5) Multi-Agent Collaboration: facilitating global map fusion across distributed agents.