aras-p/unitygaussiansplatting

Toy Gaussian Splatting visualization in Unity

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 36 minutes ago
Added to GitGenius on September 20th, 2026
Created on August 24th, 2023
Open Issues & Pull Requests: 43 (+0)
GitHub issues: Enabled
Number of forks: 484
Total Stargazers: 3,411 (+0)
Total Subscribers: 59 (+0)

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 19
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 521 days
Stale 30+ days: 19
Stale 90+ days: 18

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • bug (2)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Unity Gaussian Splatting is a real-time visualization tool for Gaussian Splatting models within the Unity game engine.

The project implements the visualization component of the 3D Gaussian Splatting technique described in the SIGGRAPH 2023 paper, allowing developers to load and display pre-computed Gaussian Splat model files in Unity. It takes already-produced splat files and renders them in real time, supporting both PLY format from the original paper and Scaniverse SPZ format. The tool includes a compression system with multiple quality presets that can reduce model sizes significantly while maintaining visual quality.

This is a suitable choice for developers working on Windows, Mac, or Linux who need to visualize Gaussian Splatting models within Unity projects. The tool works on platforms using D3D12, Metal, or Vulkan graphics APIs. It supports some virtual reality devices including HTC Vive, Varjo Aero, and Meta Quest headsets, though Apple Vision Pro and other platforms have not been tested. Mobile and web platforms are not supported. The project is explicitly positioned as a playground implementation focused on the original 2023 paper; it does not include subsequent Gaussian Splatting research developments that emerged later in 2023.

The project is in maintenance mode with no significant further development planned. The codebase is stable enough for visualization tasks but carries the caveat that platform support is limited to tested configurations, with many platforms remaining untested or known not to work.