LapisGS: Layered Progressive 3D Gaussian Splatting for Adaptive Streaming

TL;DR

LapisGS introduces a layered, progressive 3D Gaussian Splatting method that enables adaptive streaming of 3D scenes, balancing visual quality and model compactness for bandwidth-constrained XR environments.

Contribution

The paper presents a novel layered 3D Gaussian Splatting framework supporting adaptive streaming and progressive rendering, with dynamic opacity and occupancy management for efficient bandwidth use.

Findings

Up to 50.71% improvement in SSIM

286.53% improvement in LPIPS with 23% of original size

Effective balance of visual fidelity and model compactness

Abstract

The rise of Extended Reality (XR) requires efficient streaming of 3D online worlds, challenging current 3DGS representations to adapt to bandwidth-constrained environments. This paper proposes LapisGS, a layered 3DGS that supports adaptive streaming and progressive rendering. Our method constructs a layered structure for cumulative representation, incorporates dynamic opacity optimization to maintain visual fidelity, and utilizes occupancy maps to efficiently manage Gaussian splats. This proposed model offers a progressive representation supporting a continuous rendering quality adapted for bandwidth-aware streaming. Extensive experiments validate the effectiveness of our approach in balancing visual fidelity with the compactness of the model, with up to 50.71% improvement in SSIM, 286.53% improvement in LPIPS with 23% of the original model size, and shows its potential for bandwidth-adapted 3D streaming and rendering applications.