# graphdeco-inria/hierarchical-3d-gaussians

Official implementation of the SIGGRAPH 2024 paper "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets"

Repository: https://github.com/graphdeco-inria/hierarchical-3d-gaussians
Canonical: https://ross.abutalabs.com/products/hierarchical-3d-gaussians
Language: Python
License: NOASSERTION
License Family: other
Last push: 2025-06-10T08:39:35+00:00

## Health v2 (maintenance only)
Score: 35/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 26, release rhythm 35, longevity 55
- inputs: {"age_days": 782, "days_push": 449, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1461, forks 140 (observed 2026-08-28T04:04:47.462972+00:00)

## What it is
Official implementation of the SIGGRAPH 2024 paper 'A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets'. It trains hierarchical 3D Gaussian splatting models that enable real-time rendering of very large captured scenes, organized in chunks.

## Use cases
- render very large 3d captured scenes in real time
- train hierarchical 3d gaussian splatting models from photos
- novel view synthesis of large datasets
- reproduce the siggraph 2024 hierarchical 3dgs paper results
- convert and render large-scale gaussian splat scenes
- process thousands of images into a renderable 3d scene

## When to choose
- you need real-time rendering of scenes too large for standard 3D Gaussian Splatting
- you want the authoritative reference implementation of the hierarchical 3DGS paper
- you are doing research on radiance fields or large-scale scene capture

## When to avoid
- you need a production-ready, stable tool - the code is explicitly alpha
- you only need small-scene 3D Gaussian Splatting, where the original 3DGS repo is simpler
- you require a permissive license - the license is non-standard and restrictive

## Facets
- artifact type: library
- maturity: experimental
- function: graphics, machine-learning, image-processing, simulation
- domain: computer-vision, graphics, machine-learning, deep-learning
- platform: windows, python
- tags: 3d-gaussian-splatting, novel-view-synthesis, real-time-rendering, radiance-fields, research-code, siggraph-2024, large-scale-scenes, linux, gpu

## Member repositories
- graphdeco-inria/hierarchical-3d-gaussians (main) score 35

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:47.462972+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 2026-08-30T04:35:20.678225+00:00, confidence not recorded.
  - readme: https://github.com/graphdeco-inria/hierarchical-3d-gaussians (fetched 2026-08-28T04:04:47.462972+00:00, sha a9e7b2721e1e)
- Data as of 2026-08-30T08:39:29.467469+00:00.