Optimized Minimal 4D Gaussian Splatting

ICLR 2026 Conference Submission13999 Authors

Keywords: dynamic scene representation, compression, 4D Gaussian Splatting

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 $\textit{OMG4}$ (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) $\textit{Gaussian Sampling}$ to identify primitives critical to reconstruction fidelity, (2) $\textit{Gaussian Pruning}$ to remove redundancies, and (3) $\textit{Gaussian Merging}$ 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 $\textit{OMG4}$ significantly outperforms recent state-of-the-art methods, reducing model sizes by over 60\% while maintaining reconstruction quality.
These results position $\textit{OMG4}$ as a significant step forward in compact 4D scene representation, opening new possibilities for a wide range of applications.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 13999