Voyager: Real-Time Splatting City-Scale Gaussians on Resource-Constrained Devices

TL;DR

Voyager enables real-time, city-scale 3D Gaussian splatting rendering on resource-limited mobile devices by leveraging temporal correlations and preemptive filtering, achieving significant speed and energy efficiency improvements.

Contribution

The paper introduces Voyager, a novel system that accelerates city-scale 3D Gaussian splatting rendering on mobile devices using temporal-aware LoD search and preemptive rasterization filtering.

Findings

Up to 6.6× speedup over existing methods

85% energy savings on mobile devices

Maintains high rendering quality at scale

Abstract

3D Gaussian splatting (3DGS) is an emerging technique for photorealistic 3D scene rendering. However, rendering city-scale 3DGS scenes on resource-constrained mobile devices in real-time remains a significant challenge due to two compute-intensive stages: level-of-detail (LoD) search and rasterization. In this paper, we propose Voyager, an effective solution to accelerate city-scale 3DGS rendering on mobile devices. Our key insight is that, under normal user motion, the number of newly visible Gaussians within the view frustum remains roughly constant. Leveraging this temporal correlation, we propose a temporal-aware LoD search to identify the necessary Gaussians for the remaining rendering stages. For the remaining rendering process, we accelerate the bottleneck stage, rasterization, via preemptive $\alpha$-filtering. With all optimizations above, our system can deliver low-latency, city-scale 3DGS rendering on mobile devices. Compared to existing solutions, Voyager achieves up to 6.6$\times$ speedup and 85\% energy savings with superior rendering quality.