manycoretech/aholo-viewer

A high performance 3DGS renderer

What it solves

Aholo Viewer provides a high-performance way to render 3D Gaussian Splatting (3DGS) and Mesh data, specifically addressing the challenge of handling extremely large 3DGS datasets that would otherwise be too heavy for standard renderers.

How it works

The project uses a "Chunked Streaming LOD (Level of Detail)" schema. This allows the viewer to stream and render only the necessary parts of a huge 3DGS scene based on the level of detail required, rather than loading the entire dataset at once.

Who it’s for

It is designed for developers building 3D applications that need to display high-fidelity 3DGS or mesh data efficiently in a web environment.

Highlights

  • High-performance rendering for both 3DGS and Mesh.
  • Implements Chunked Streaming LOD to support massive datasets.
  • Includes a dedicated TypeScript renderer package and a documentation website with an interactive playground.

Related

  • Project
    reall3d-com/Reall3dViewer

    A Three.js-based Web renderer for 3D Gaussian Splatting that enables high-performance streaming and adaptive LOD for large-scale 3D scenes.

  • Project
    playcanvas/supersplat-viewer

    A web-based viewer for Gaussian Splatting scenes that allows developers to embed high-performance 3D splat assets into static websites using WebGPU or WebGL.

  • Project
    Linketic/CityGaussian

    A framework for high-quality, large-scale 3D scene reconstruction using Gaussian Splatting, featuring multi-GPU support and geometrically accurate rendering.

  • Project
    Visionary-Laboratory/visionary

    A WebGPU-powered platform for real-time rendering of Gaussian Splatting variants and 3D meshes directly in the browser using ONNX Runtime.

  • Project
    Kiri-Innovation/3dgs-render-blender-addon

    A Blender add-on for importing, editing, animating, and rendering 3D Gaussian Splats, integrating high-fidelity 3D captures into a standard 3D production workflow.