Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes

TL;DR

This paper introduces TC3DGS, a novel method for compressing dynamic 3D Gaussian representations that significantly reduces memory usage while maintaining visual quality, enabling real-time rendering for complex scenes.

Contribution

The paper presents a new compression technique for dynamic 3D Gaussian splatting that combines pruning, mixed-precision quantization, and trajectory interpolation to enhance efficiency.

Findings

Achieves up to 67x compression with minimal quality loss.

Effectively handles scenes with complex motions and long sequences.

Maintains visual fidelity comparable to uncompressed methods.

Abstract

Recent advancements in high-fidelity dynamic scene reconstruction have leveraged dynamic 3D Gaussians and 4D Gaussian Splatting for realistic scene representation. However, to make these methods viable for real-time applications such as AR/VR, gaming, and rendering on low-power devices, substantial reductions in memory usage and improvements in rendering efficiency are required. While many state-of-the-art methods prioritize lightweight implementations, they struggle in handling {scenes with complex motions or long sequences}. In this work, we introduce Temporally Compressed 3D Gaussian Splatting (TC3DGS), a novel technique designed specifically to effectively compress dynamic 3D Gaussian representations. TC3DGS selectively prunes Gaussians based on their temporal relevance and employs gradient-aware mixed-precision quantization to dynamically compress Gaussian parameters. In addition, TC3DGS exploits an adapted version of the Ramer-Douglas-Peucker algorithm to further reduce storage by interpolating Gaussian trajectories across frames. Our experiments on multiple datasets demonstrate that TC3DGS achieves up to 67$\times$ compression with minimal or no degradation in visual quality. More results and videos are provided in the supplementary. Project Page: https://ahmad-jarrar.github.io/tc-3dgs/