SplatBus: A Gaussian Splatting Viewer Framework via GPU Interprocess Communication

TL;DR

SplatBus introduces a GPU-based Gaussian splatting framework that leverages interprocess communication APIs to facilitate easy integration with popular rendering tools, enabling real-time, high-fidelity rendering for interactive applications.

Contribution

It presents a novel GPU-based framework that simplifies integration of 3D Gaussian splatting into traditional rendering pipelines using IPC APIs.

Findings

Enables real-time rendering with high fidelity.

Facilitates integration with tools like Unity, Blender, Unreal.

Supports applications in VR, AR, robotics.

Abstract

Radiance field-based rendering methods have attracted significant interest from the computer vision and computer graphics communities. They enable high-fidelity rendering with complex real-world lighting effects, but at the cost of high rendering time. 3D Gaussian Splatting solves this issue with a rasterisation-based approach for real-time rendering, enabling applications such as autonomous driving, robotics, virtual reality, and extended reality. However, current 3DGS implementations are difficult to integrate into traditional mesh-based rendering pipelines, which is a common use case for interactive applications and artistic exploration. To address this limitation, this software solution uses Nvidia's interprocess communication (IPC) APIs to easily integrate into implementations and allow the results to be viewed in external clients such as Unity, Blender, Unreal Engine, and OpenGL viewers. The code is available at https://github.com/RockyXu66/splatbus.