VR Escape Room Game Powered by GS-Verse 3DGS Engine

Table of Contents

VR Escape Room Game Powered by GS-Verse 3DGS Engine

An exciting new project has emerged in the space of real-time 3D rendering and interactive VR gaming: Escape Room (GS-Verse). Built on top of the GS-Verse Gaussian Splatting engine, this VR escape room demonstrates the potential of incorporating 3D Gaussian Splatting (3DGS) representations inside interactive gaming setups.

Project Overview

The game is built using Unity 2022.3.47f1 along with OpenXR and the XR Interaction Toolkit, targeting immersive virtual reality headsets. It challenges players to solve interactive puzzles (such as a Fibonacci sequence puzzle, a keypad safe puzzle, and bookshelf navigation) in a fully reconstructed, photorealistic environment powered by 3D Gaussian Splatting shaders.

Engine and Technical Details

The Gaussian Splatting rendering pipeline is integrated as a Unity Package Manager (UPM) dependency pointing to a specialized fork of GS-Verse pinned to the escape-room-v1 tag.

Because the project relies on high-performance Gaussian Splatting shaders compiled via DXC, the Unity engine targets D3D with DXC from a Windows editor environment. CI/CD builds are automated using a self-hosted Windows runner executing headless Unity builds and packaging them into a single-file installer via Inno Setup 6.

For more details, check out the GS-escape-room GitHub repository.

Escape room with the Fibonacci puzzle and palm
Desk with the faculty banner and a keypad puzzle Shelf with the safe puzzle and crate

Related Posts

Piotr Borycki and Kornel Howil at PRE-NeurIPS 2025

Piotr Borycki and Kornel Howil at PRE-NeurIPS 2025 Piotr Borycki and Kornel Howil participated in PRE-NeurIPS 2025, actively representing the group and presenting the latest research achievements of the team.

Read More

E3DGSAR at PP-RAI 2026 in Kraków

E3DGSAR at PP-RAI 2026 in Kraków From April 20 to April 22, 2026, the Faculty of Computer Science at the AGH University of Krakow hosted the 7th Polish Conference on Artificial Intelligence (PP-RAI 2026). As one of the most prominent events on artificial intelligence and machine learning in Poland, it gathered top researchers, industry experts, and students from across the country.

Read More
PR-ENDO: Physically Based Relightable Gaussian Splatting for Endoscopy

PR-ENDO: Physically Based Relightable Gaussian Splatting for Endoscopy

Abstract Endoluminal endoscopic imaging—used in diagnosing colorectal cancer and other internal diseases—stands to benefit greatly from accurate 3D reconstructions and novel-view synthesis. However, current methods struggle with artifacts due to constrained camera trajectories and lighting effects that depend heavily on view, often overfitting and failing when viewing from novel angles.

Read More