Compression in 3D Gaussian Splatting: A Survey of Methods, Trends, and Future Directions

2025-02-26

AI Summary

While 3D Gaussian Splatting (3DGS) enables real-time rendering and high editability, its substantial memory footprint and storage overhead severely hinder deployment on resource-constrained edge devices. Method: We systematically survey over twenty state-of-the-art compression techniques, establishing the first comprehensive taxonomy of 3DGS compression methodologies. We further propose a topology-aware, cross-method evaluation framework and integrate insights from NeRF lightweighting to analyze trade-offs among compression ratio (>15×, <100 MB/scene), visual fidelity, and computational efficiency. Contribution/Results: Our analysis identifies dynamic Gaussian culling and implicit-explicit hybrid representations as pivotal directions for breakthrough compression. The taxonomy and evaluation framework provide both theoretical foundations and practical guidelines for scalable 3DGS deployment—enabling efficient, high-fidelity rendering under strict memory and latency constraints.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Data Compression

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

3D Gaussian Splatting (3DGS) has recently emerged as a pioneering approach in explicit scene rendering and computer graphics. Unlike traditional neural radiance field (NeRF) methods, which typically rely on implicit, coordinate-based models to map spatial coordinates to pixel values, 3DGS utilizes millions of learnable 3D Gaussians. Its differentiable rendering technique and inherent capability for explicit scene representation and manipulation positions 3DGS as a potential game-changer for the next generation of 3D reconstruction and representation technologies. This enables 3DGS to deliver real-time rendering speeds while offering unparalleled editability levels. However, despite its advantages, 3DGS suffers from substantial memory and storage requirements, posing challenges for deployment on resource-constrained devices. In this survey, we provide a comprehensive overview focusing on the scalability and compression of 3DGS. We begin with a detailed background overview of 3DGS, followed by a structured taxonomy of existing compression methods. Additionally, we analyze and compare current methods from the topological perspective, evaluating their strengths and limitations in terms of fidelity, compression ratios, and computational efficiency. Furthermore, we explore how advancements in efficient NeRF representations can inspire future developments in 3DGS optimization. Finally, we conclude with current research challenges and highlight key directions for future exploration.

Problem

• Compression methods for 3D Gaussian Splatting
• Memory and storage challenges in 3DGS
• Future optimization inspired by NeRF advancements

Innovation

• Utilizes learnable 3D Gaussians
• Focuses on scalability and compression
• Explores efficient NeRF representations