GS-NFS: Bandwidth-adaptive Streaming of Dynamic Gaussian Splats and Point Clouds

2026-06-03

AI Summary

This work addresses the challenge of real-time streaming for dynamic 3D Gaussian Splatting (3DGS) videos, which generate massive data volumes that existing compression methods struggle to handle efficiently. To overcome this limitation, we propose a GPU-optimized parallelized codec framework that leverages efficient spatial and attribute encoding strategies to enable real-time compression and decompression of dynamic 3DGS and point cloud sequences. Our approach achieves competitive compression ratios while preserving high rendering fidelity, accelerating encoding and decoding speeds by one to two orders of magnitude compared to prior methods. Notably, it is the first to support full-frame-rate real-time 3D video streaming and incorporates adaptive bandwidth capabilities for practical deployment in varying network conditions.

Abstract

Dynamic 3D Gaussian Splatting (3DGS) holds great promise as a 3D video streaming technology since it can represent complex 3D scenes with high fidelity. In this approach, every frame in a 3D video represents the environment as a collection of Gaussians with position and other attributes such as scale, rotation, opacity, and color. Frames capture fine details, permit views from any arbitrary perspective, but are an order of magnitude, or more, larger than 2D video frames. A line of recent work has explored how to compress dynamic 3DGS frames, but these approaches are often slow, in part because their compression techniques are not amenable to efficient acceleration. GS-NFS accelerates dynamic 3DGS compression and decompression on a GPU, to the point where it can encode and decode at full frame rate. It achieves this by developing novel GPU-based parallelizations of existing algorithms for encoding both positions and attributes of Gaussians. As a result, it is 1-2 orders of magnitude faster than the state-of-the-art in encoding and decoding a frame, while offering competitive compression performance and rendering quality.

Problem

• Dynamic 3D Gaussian Splatting
• 3D video streaming
• compression
• real-time performance
• bandwidth

Innovation

• Dynamic 3D Gaussian Splatting
• GPU acceleration
• real-time compression
• parallel encoding
• bandwidth-adaptive streaming