Optimized Minimal 4D Gaussian Splatting

2025-10-04

AI Summary

4D Gaussian Splatting demands millions of Gaussian primitives for high-fidelity dynamic scene reconstruction, incurring prohibitive storage overhead. To address this, we propose OMG4—a novel framework that integrates progressive three-stage Gaussian optimization (sampling → pruning → merging) with implicit appearance compression and scalable subvector quantization (SVQ) for efficient lossy compression. Our key contributions are: (1) joint geometric simplification and implicit appearance encoding, enabling co-optimized preservation of geometry and color fidelity during compression; and (2) a hierarchical SVQ scheme explicitly designed to match the statistical distribution of Gaussian attributes, significantly improving the rate-distortion trade-off. Evaluated on standard dynamic scene benchmarks, OMG4 achieves over 60% model size reduction while surpassing state-of-the-art methods in PSNR and SSIM—demonstrating exceptional visual fidelity alongside ultra-low storage cost.

Technology Category

• Data Mining & Knowledge Management: Data Compression
• Search and Optimization: Sampling/Simulation-based Search
• Computer Vision: 3D Computer Vision

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
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

4D Gaussian Splatting has emerged as a new paradigm for dynamic scene representation, enabling real-time rendering of scenes with complex motions. However, it faces a major challenge of storage overhead, as millions of Gaussians are required for high-fidelity reconstruction. While several studies have attempted to alleviate this memory burden, they still face limitations in compression ratio or visual quality. In this work, we present OMG4 (Optimized Minimal 4D Gaussian Splatting), a framework that constructs a compact set of salient Gaussians capable of faithfully representing 4D Gaussian models. Our method progressively prunes Gaussians in three stages: (1) Gaussian Sampling to identify primitives critical to reconstruction fidelity, (2) Gaussian Pruning to remove redundancies, and (3) Gaussian Merging to fuse primitives with similar characteristics. In addition, we integrate implicit appearance compression and generalize Sub-Vector Quantization (SVQ) to 4D representations, further reducing storage while preserving quality. Extensive experiments on standard benchmark datasets demonstrate that OMG4 significantly outperforms recent state-of-the-art methods, reducing model sizes by over 60% while maintaining reconstruction quality. These results position OMG4 as a significant step forward in compact 4D scene representation, opening new possibilities for a wide range of applications. Our source code is available at https://minshirley.github.io/OMG4/.

Problem

• Reduces storage overhead in 4D Gaussian Splatting
• Prunes and merges Gaussians to compress models
• Maintains reconstruction quality while minimizing model size

Innovation

• Progressive three-stage pruning for compact Gaussians
• Implicit appearance compression for storage reduction
• Generalized Sub-Vector Quantization to 4D representations