Voyager: Real-Time Splatting City-Scale 3D Gaussians on Resource-Constrained Devices

Zheng liu, He Zhu, Xingyang Li, Yirun Wang, Yiming Gan, Wei Li, Yujiao Shi, Jingwen Leng, Minyi Guo, Yu Feng

Keywords: Acceleration for 3D Gaussian splatting

TL;DR: We propose an efficient and fast rendering algorithm for city-scale 3DGS scenes. Our algorithm achieves real-time rendering on resource-constrained mobile devices with up to 6.6x speedup on city-scale datasets.

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. Codes will be released upon publication.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 1358