antimatter15/splat

WebGL 3D Gaussian Splat Viewer

View on GitHub ↗Jump to charts ↓

antimatter15/splat has 3k+ stars and 300+ forks on GitHub, is written in JavaScript, and was last pushed on Nov 16, 2025. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 11 minutes ago
Added to GitGenius on September 22nd, 2026
Created on September 11th, 2023
Open Issues & Pull Requests: 37 (+0)
GitHub issues: Enabled
Number of forks: 337
Total Stargazers: 3,074 (+0)
Total Subscribers: 30 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 83.8 days
Mean response time: 166.2 days
90th percentile: 363.3 days
Tracked items: 10

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 12
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 548 days
Stale 30+ days: 12
Stale 90+ days: 12

Recent activity

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

Top labels

No label distribution available yet.

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

Splat is a WebGL 3D Gaussian Splat Viewer that renders photorealistic 3D scenes in the browser using 3D Gaussian Splatting, a technique for converting photographs into navigable 3D environments.

The tool solves the problem of efficiently displaying 3D Gaussian Splatting scenes on standard graphics hardware. Rather than using earlier techniques like Neural Radiance Fields that require expensive computation, this approach treats the rendered output as an extension of point cloud rendering, which graphics cards can process very efficiently. Users can load scenes by providing a URL to a CORS-accessible .splat file, or by dragging and dropping .ply files processed with 3D Gaussian Splatting software, which the viewer automatically converts to the .splat format.

The viewer suits developers and researchers who want to display Gaussian Splatting scenes on the web without heavy computational requirements. It works well for embedding photorealistic 3D models in web applications, galleries, or documentation. The README acknowledges that for projects requiring animations, multiple format support, and advanced features, an alternative renderer may be more suitable. The tool provides extensive navigation controls across desktop and mobile platforms, including keyboard movement, camera manipulation via mouse and trackpad, and touch gestures. Users can save view coordinates to URLs and load multiple camera positions from a cameras.json file.

Development activity shows consistent engagement with the codebase through regular commits addressing both features and fixes. The project maintains responsiveness to user issues and pull requests, indicating active maintenance. Updates reflect both technical improvements to the renderer and expansion of supported workflows, such as enhanced file format handling and control scheme refinements.