huggingface/gsplat.js

JavaScript Gaussian Splatting library.

What it solves

It provides a simple way to render 3D Gaussian Splatting data in web browsers, offering a general-purpose library similar to how three.js works for traditional 3D graphics.

How it works

The library uses WebGL to render 3D Gaussian Splats. It provides a set of components—including a Scene, Camera, WebGLRenderer, and OrbitControls—to load and display 3D data. It supports loading .ply files and a more compact .splat format for faster loading times.

Who it’s for

Web developers who want to integrate high-quality 3D Gaussian Splatting visualizations into their websites or applications without needing to build a rendering engine from scratch.

Highlights

  • Easy Setup: Quick start via NPM and compatibility with ES6 modules and bundlers like Vite.
  • Flexible Data Formats: Supports both standard .ply files and optimized .splat files.
  • Conversion Tools: Includes examples for converting between .ply and .splat formats.
  • Real-time Interaction: Includes orbit controls for navigating 3D scenes.

Related

  • Project
    InsightSoftwareConsortium/ITK

    An open-source, cross-platform toolkit for N-dimensional scientific image processing, segmentation, and registration, primarily used for medical image analysis.

  • Project
    yoshitomo-matsubara/torchdistill

    torchdistill is a PyTorch‑based library that lets you run knowledge‑distillation experiments (teacher‑student training) by writing only a YAML configuration. It provides many modern KD losses, a forward‑hook manager for extracting intermediate features, and example scripts for vision and NLP tasks. Install via `pip install torchdistill` and cite the associated papers when used in research.

  • Project
    secluso/core

    A private, DIY home security camera system for Raspberry Pi that uses end-to-end encryption to avoid cloud surveillance.

  • Project
    lightly-ai/lightly-train

    A computer vision framework for pretraining, fine-tuning, and distilling SOTA models like DINOv3 and LTDETRv2 for tasks such as object detection and segmentation.