GS-Cache: A GS-Cache Inference Framework for Large-scale Gaussian Splatting Models

TL;DR

GS-Cache is an optimized inference framework that significantly accelerates large-scale 3D Gaussian Splatting rendering, enabling real-time, high-quality VR experiences on consumer hardware.

Contribution

It introduces a cache-centric pipeline, an efficiency-aware scheduler, and optimized CUDA kernels to enhance 3D Gaussian Splatting performance for real-time applications.

Findings

Achieves up to 5.35x performance improvement

Reduces latency by 35%

Lowers GPU memory usage by 42%

Abstract

Rendering large-scale 3D Gaussian Splatting (3DGS) model faces significant challenges in achieving real-time, high-fidelity performance on consumer-grade devices. Fully realizing the potential of 3DGS in applications such as virtual reality (VR) requires addressing critical system-level challenges to support real-time, immersive experiences. We propose GS-Cache, an end-to-end framework that seamlessly integrates 3DGS's advanced representation with a highly optimized rendering system. GS-Cache introduces a cache-centric pipeline to eliminate redundant computations, an efficiency-aware scheduler for elastic multi-GPU rendering, and optimized CUDA kernels to overcome computational bottlenecks. This synergy between 3DGS and system design enables GS-Cache to achieve up to 5.35x performance improvement, 35% latency reduction, and 42% lower GPU memory usage, supporting 2K binocular rendering at over 120 FPS with high visual quality. By bridging the gap between 3DGS's representation power and the demands of VR systems, GS-Cache establishes a scalable and efficient framework for real-time neural rendering in immersive environments.