SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting

2025-12-08

AI Summary

3D Gaussian Splatting (3DGS) enables high-fidelity, real-time rendering but suffers from prohibitive storage and computational overhead due to its dense Gaussian point representation—especially in 4D dynamic scenes. To address this, we propose the first unified efficiency-optimization taxonomy for both static and dynamic 3DGS, categorizing techniques into two orthogonal paradigms: parameter compression and structural reconstruction. We establish a standardized evaluation benchmark encompassing major datasets, metrics, and baselines, enabling quantitative analysis of the trade-offs among compression ratio, rendering quality (e.g., PSNR, SSIM, LPIPS), and inference speed. Furthermore, we conduct a comprehensive survey of the technical evolution, delivering the most complete empirical performance comparison and systematic diagnosis of current limitations. This work provides both theoretical foundations and practical guidelines for deploying high-fidelity, real-time 3D scene representations in resource-constrained settings.

Technology Category

• Computer Vision: 3D Computer Vision
• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

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

Abstract

3D Gaussian Splatting (3DGS) has emerged as a powerful explicit representation enabling real-time, high-fidelity 3D reconstruction and novel view synthesis. However, its practical use is hindered by the massive memory and computational demands required to store and render millions of Gaussians. These challenges become even more severe in 4D dynamic scenes. To address these issues, the field of Efficient Gaussian Splatting has rapidly evolved, proposing methods that reduce redundancy while preserving reconstruction quality. This survey provides the first unified overview of efficient 3D and 4D Gaussian Splatting techniques. For both 3D and 4D settings, we systematically categorize existing methods into two major directions, Parameter Compression and Restructuring Compression, and comprehensively summarize the core ideas and methodological trends within each category. We further cover widely used datasets, evaluation metrics, and representative benchmark comparisons. Finally, we discuss current limitations and outline promising research directions toward scalable, compact, and real-time Gaussian Splatting for both static and dynamic 3D scene representation.

Problem

• Reducing memory and computational demands of 3D Gaussian Splatting
• Addressing efficiency challenges in 4D dynamic scene representation
• Surveying compression methods for compact and real-time rendering

Innovation

• Parameter Compression reduces Gaussian storage redundancy
• Restructuring Compression reorganizes Gaussian data structure
• Unified framework for efficient 3D and 4D Gaussian Splatting