# mkkellogg/GaussianSplats3D

Three.js-based implementation of 3D Gaussian splatting

Repository: https://github.com/mkkellogg/GaussianSplats3D
Canonical: https://ross.abutalabs.com/products/gaussiansplats3d
Language: JavaScript
License: MIT
License Family: permissive
Topics: gaussian-splatting, three-js, webgl, threejs, 3d-gaussian-splatting, javascript
Last push: 2025-10-19T22:58:20+00:00

## Health v2 (maintenance only)
Score: 46/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 47, release rhythm 28, longevity 76
- inputs: {"age_days": 1073, "days_push": 318, "days_rel": 585, "gap_med": 64.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2870, forks 378 (observed 2026-08-28T04:07:27.090041+00:00)

## What it is
A Three.js-based renderer for 3D Gaussian splatting scenes, viewable in real time in the browser. It supports .ply, .splat, and a custom compressed .ksplat format, with WASM/GPU-accelerated sorting and WebXR support.

## Use cases
- view 3D gaussian splatting scenes in a web browser
- render radiance field captures from photogrammetry in three.js
- convert ply splat files to a compressed web-friendly format
- embed interactive 3D captured scenes in a web app
- view gaussian splats in VR with WebXR
- mix gaussian splat scenes with regular three.js objects

## When to choose
- you need gaussian splat rendering inside an existing Three.js scene
- you want a browser-based splat viewer with WebXR support
- you need to load .ply, .splat, or .ksplat splat files on the web

## When to avoid
- you need a project in active development - the author recommends Spark instead
- you need CUDA-native rendering performance for training or offline rendering
- you need WebGPU-only features

## Facets
- artifact type: library
- maturity: maintenance
- function: graphics, image-processing, wasm
- domain: graphics, web-development, computer-vision, frontend
- platform: browser
- tags: gaussian-splatting, threejs, webgl, 3d-rendering, radiance-fields, webxr, point-clouds, web-server, javascript

## Member repositories
- mkkellogg/GaussianSplats3D (main) score 46

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:27.090041+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:48:28.181013+00:00, confidence not recorded.
  - readme: https://github.com/mkkellogg/GaussianSplats3D (fetched 2026-08-28T04:07:27.090041+00:00, sha e148c1fd8f4b)
- Data as of 2026-08-30T08:39:29.467469+00:00.