VRSplat: Fast and Robust Gaussian Splatting for Virtual Reality
Xuechang Tu, Lukas Radl, Michael Steiner, Markus Steinberger, Bernhard Kerbl, Fernando de la Torre

TL;DR
VRSplat is a novel 3D Gaussian Splatting technique optimized for virtual reality, addressing key VR challenges like popping, distortions, and low framerates, enabling real-time, high-quality VR rendering.
Contribution
We introduce VRSplat, combining recent 3DGS advancements with new optimizations to support robust, real-time VR rendering with improved visual stability and efficiency.
Findings
Achieves over 72 FPS in VR environments
Eliminates popping and floaters effectively
Preferred by users in controlled studies
Abstract
3D Gaussian Splatting (3DGS) has rapidly become a leading technique for novel-view synthesis, providing exceptional performance through efficient software-based GPU rasterization. Its versatility enables real-time applications, including on mobile and lower-powered devices. However, 3DGS faces key challenges in virtual reality (VR): (1) temporal artifacts, such as popping during head movements, (2) projection-based distortions that result in disturbing and view-inconsistent floaters, and (3) reduced framerates when rendering large numbers of Gaussians, falling below the critical threshold for VR. Compared to desktop environments, these issues are drastically amplified by large field-of-view, constant head movements, and high resolution of head-mounted displays (HMDs). In this work, we introduce VRSplat: we combine and extend several recent advancements in 3DGS to address challenges of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputer Graphics and Visualization Techniques · Video Surveillance and Tracking Methods
MethodsFocus
