Thin-Client Interactive Gaussian Adaptive Streaming over HTTP/3

2026-05-09

AI Summary

This work addresses the challenge of deploying 3D Gaussian Splatting (3DGS) on mobile and extended reality devices due to its high computational and bandwidth demands. The authors propose TIGAS, the first remote streaming architecture for 3DGS that supports full six-degree-of-freedom (6DoF) interaction. TIGAS offloads rasterization to a backend server and streams viewpoint-dependent 2D projections to a lightweight web client over HTTP/3/QUIC. An adaptive bitrate (ABR) algorithm dynamically adjusts rendering quality in response to network fluctuations. Integrated with a WebGPU-based super-resolution pipeline, the system achieves an average SSIM of 0.88 across multi-continental experiments, with per-frame backend rendering latency under 10 milliseconds, thereby meeting the stringent low-latency requirements of interactive 6DoF applications.

Abstract

Recent advancements in 3D Gaussian Splatting (3DGS) have enabled photorealistic rendering of complex scenes, yet widespread adoption on mobile and Extended Reality (XR) devices is hindered by substantial computational and bandwidth requirements. While existing solutions often focus on model compression for client-side rendering, they still demand significant GPU power, limiting applicability on resource-constrained hardware. We propose TIGAS (Thin-client Interactive Gaussian Adaptive Streaming), a remote rendering framework offloading rasterization to a backend. To bypass the prohibitive latencies connected to fluctuating network conditions, TIGAS streams view-dependent 2D projections to a lightweight web client over QUIC, minimizing head-of-line (HoL) blocking. A dedicated ABR algorithm adapts rendering quality to fluctuating network conditions, maintaining motion-to-photon latency within strict 6DoF interactive constraints. Furthermore, we discuss the integration of an experimental WebGPU super-resolution pipeline to analyze the trade-offs between perceptual quality enhancements and thin-client processing bottlenecks. We extensively evaluate TIGAS across multi-continental environments using 14 3DGS models and real 6DoF EyeNavGS movement traces. Powered by a backend rendering frames in under 10 milliseconds, TIGAS maintains latency within interactive thresholds while achieving an average SSIM of 0.88, serving both as a robust testbed for 3DGS streaming research and a capable delivery system. The source code is available at: https://github.com/Rekenar/GaussianAdaptiveStreamer.

Problem

• 3D Gaussian Splatting
• Thin-client Streaming
• Interactive Latency
• 6DoF
• Resource-constrained Devices

Innovation

• 3D Gaussian Splatting
• Thin-client Streaming
• QUIC
• Adaptive Bitrate
• Remote Rendering