3DGS.zip: A survey on 3D Gaussian Splatting Compression Methods

2024-06-17

arXiv.org

AI Summary

3D Gaussian Splatting (3DGS) suffers from excessive memory and storage overhead, hindering deployment on mobile and AR devices. To address this bottleneck, we propose the first unified evaluation framework that explicitly distinguishes compression (reducing file size) from pruning (reducing Gaussian count), establishing a cross-method comparable benchmark. Our systematic lightweighting approach integrates quantization, sparsification, structured pruning, attribute encoding, and optimization-driven Gaussian reparameterization. Extensive experiments on standard datasets demonstrate MB-scale model size reduction, over 50% fewer Gaussians, and negligible rendering quality degradation. Key contributions include: (1) a formal taxonomy for 3DGS lightweighting; (2) an open-source, reproducible evaluation framework; and (3) Pareto-optimal trade-offs between accuracy and efficiency—enabling practical on-device 3DGS deployment.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• 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

Abstract

3D Gaussian Splatting (3DGS) has emerged as a cutting-edge technique for real-time radiance field rendering, offering state-of-the-art performance in terms of both quality and speed. 3DGS models a scene as a collection of three-dimensional Gaussians, with additional attributes optimized to conform to the scene's geometric and visual properties. Despite its advantages in rendering speed and image fidelity, 3DGS is limited by its significant storage and memory demands. These high demands make 3DGS impractical for mobile devices or headsets, reducing its applicability in important areas of computer graphics. To address these challenges and advance the practicality of 3DGS, this survey provides a comprehensive and detailed examination of compression and compaction techniques developed to make 3DGS more efficient. We classify existing methods into two categories: compression, which focuses on reducing file size, and compaction, which aims to minimize the number of Gaussians. Both methods aim to maintain or improve quality, each by minimizing its respective attribute: file size for compression and Gaussian count for compaction. We introduce the basic mathematical concepts underlying the analyzed methods, as well as key implementation details and design choices. Our report thoroughly discusses similarities and differences among the methods, as well as their respective advantages and disadvantages. We establish a consistent framework for comparing the surveyed methods based on key performance metrics and datasets. Specifically, since these methods have been developed in parallel and over a short period of time, currently, no comprehensive comparison exists. This survey, for the first time, presents a unified framework to evaluate 3DGS compression techniques. We maintain a website that will be regularly updated with emerging methods: https://w-m.github.io/3dgs-compression-survey/ .

Problem

• Addresses high storage and memory demands of 3D Gaussian Splatting.
• Explores compression and compaction techniques for 3DGS efficiency.
• Provides a unified framework to evaluate 3DGS compression methods.

Innovation

• Compression reduces 3DGS file size efficiently.
• Compaction minimizes Gaussian count in 3DGS.
• Unified framework evaluates 3DGS compression techniques.