Creating Virtual Environments with 3D Gaussian Splatting: A Comparative Study
Shi Qiu, Binzhu Xie, Qixuan Liu, Pheng-Ann Heng
TL;DR
3D Gaussian Splatting (3DGS) offers an explicit, scalable 3D representation suitable for real-time rendering, but its practical effectiveness for VE creation in XR remained underexplored. This paper conducts a comparative study of three 3DGS-based VE pipelines: novel view synthesis, mesh reconstruction, and panoramic 3D scene generation, implemented with COLMAP, SuGaR, and depth-based panorama strategies, and rendered in Unity. The authors evaluate visual fidelity, performance, and user immersion, reporting real-time performance on high-end hardware and that novel view synthesis yields the strongest immersion while highlighting limitations in object-level interaction and free movement. These findings demonstrate the viability of 3DGS for XR VEs and provide guidance on when to use each pipeline and where future improvements are needed.
Abstract
3D Gaussian Splatting (3DGS) has recently emerged as an innovative and efficient 3D representation technique. While its potential for extended reality (XR) applications is frequently highlighted, its practical effectiveness remains underexplored. In this work, we examine three distinct 3DGS-based approaches for virtual environment (VE) creation, leveraging their unique strengths for efficient and visually compelling scene representation. By conducting a comparable study, we evaluate the feasibility of 3DGS in creating immersive VEs, identify its limitations in XR applications, and discuss future research and development opportunities.