发表机构
Christian Doppler Laboratory ATHENA, Alpen-Adria Universität Klagenfurt; Université de Lorraine, CNRS, Inria, LORIA; Universidade Estadual de Campinas (UNICAMP)（克拉根福阿尔卑斯-亚得里亚大学; 洛林大学; 坎皮纳斯州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MoQSplat提出基于MoQ的3DGS自适应渐进流传输，通过空间轨道、语义组和渐进子组映射到独立QUIC流，消除队头阻塞，并利用订阅者驱动循环按6-DoF视锥动态请求，实验证明不透明度剪枝更优。
AI 中文摘要
3D高斯泼溅（3DGS）能够实现照片级逼真的新视角合成，但传输千兆字节规模的场景数据对于沉浸式应用而言仍具挑战性。传统的基于TCP的HTTP自适应流传输会引入队头（HOL）阻塞，且粗粒度的分段方式不适合精细的3DGS传输。我们提出MoQSplat，将3DGS内容映射到基于QUIC的媒体传输（MoQ）层次结构上。MoQSplat将场景划分为空间轨道（Tracks），将高斯溅射聚类为语义连贯的组（Groups），并构建渐进质量的子组（Subgroups），映射到独立的QUIC流上，以消除连接级别的HOL阻塞。通过无状态的、订阅者驱动的自适应循环，客户端基于六自由度（6-DoF）视锥可见性、距离和中央凹对齐动态请求空间区域和质量层级。我们在原型实现上评估了核心组件，结果表明基于不透明度的剪枝在渐进式传输中优于基于尺度的剪枝。源代码可在该https URL获取。
英文摘要
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.
Comments7 pages. Accepted at IEEE MMSP 2026 (Istanbul, 22-24 September 2026). First three authors contributed equally. Code: https://github.com/emanuele-artioli/MoQSplat
