MoQSplat: Adaptive Progressive Streaming of 3D Gaussian Splatting via MoQ

2026-09-16

AI Summary

为解决3D高斯点绘数据传输难题，提出MoQSplat方法，通过Media over QUIC分层传输，实现基于客户端动态请求的自适应渐进式流媒体服务。

Abstract

3D Gaussian Splatting (3DGS) enables photorealistic novel view synthesis, but transmitting gigabyte-scale scene data remains challenging for immersive applications. Traditional HTTP Adaptive Streaming over TCP introduces Head-of-Line (HOL) blocking and coarse segmenting ill-suited to fine-grained 3DGS delivery. We propose MoQSplat, which maps 3DGS content onto the Media over QUIC (MoQ) transport hierarchy. MoQSplat partitions scenes into spatial Tracks, clusters splats into semantically coherent Groups, and constructs progressive-quality Subgroups mapped to independent QUIC streams to eliminate connection-level HOL blocking. Using a stateless, subscriber-driven adaptation loop, clients dynamically request spatial regions and quality tiers based on six degrees of freedom (6-DoF) frustum visibility, distance, and foveal alignment. We evaluate the core components on a prototype implementation, showing that opacity-based pruning outperforms scale-based pruning for progressive delivery. The source code is available at https://github.com/emanuele-artioli/MoQSplat.

Problem

• 3D Gaussian Splatting
• HTTP Adaptive Streaming
• HOL blocking

Innovation

• MoQSplat
• QUIC
• Adaptive Streaming
• 3D Gaussian Splatting
• Progressive Delivery