LibreAI / IA 3D / 3D Gaussian Splatting
// ai-3d · graphdeco-inria/gaussian-splatting

3D Gaussian Splatting

3D Gaussian Splatting est un projet de IA 3D, créé par graphdeco-inria (graphdeco-inria/gaussian-splatting sur GitHub). Il compte 24 460 étoiles sur GitHub et 3 494 forks, il est publié sous les conditions « Research-only », et a été mis à jour pour la dernière fois sur GitHub le 17 octobre 2025.

The official SIGGRAPH 2023 implementation — real-time radiance fields at 30+ fps from ordinary photos, research licence

★ 24,5 k étoiles⑂ 3,5 k forksResearch-onlymis à jour oct. 2025
▦ visuel — le README de ce projet ne contient aucune capture intégrable,
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.
// détails du projet

Détails du projet

Étoiles GitHub
24 460
Forks
3 494
Licence
Research-only
Dernière mise à jour sur GitHub
17 octobre 2025
Catégorie
IA 3D
Type de fiche
Guide d'installation complet
Site officiel
Project page
// fonctionnement

Comment ça marche

  1. Clone with submodules

    The repo contains submodules, so clone it recursively.

  2. Create the conda environment

    Build the environment from the provided file and activate it.

  3. Prepare your photos

    Use the included script to turn a set of photos into SfM inputs, or start from the sample datasets.

  4. Train, then view in real time

    Train the model, then open the real-time viewer and fly through the scene at 30+ fps.

// fonctionnalités

Pourquoi on l'adore

Real-time radiance fields

Novel-view synthesis at 30 fps or more in 1080p — the headline result of the paper.

State-of-the-art quality

Matches or beats NeRF-style methods on established datasets while training faster.

Live training viewer

A network viewer lets you watch the optimisation as it happens.

OpenGL real-time viewer

Render trained scenes interactively, with a top view and VR support added since release.

Your own photos in

A helper script converts ordinary photo sets into optimisation-ready SfM data.

// lancez-le

Lancez-le vous-même

  1. Step 1 — Clone recursively

    Submodules are required, so use the --recursive flag.

    git clone https://github.com/graphdeco-inria/gaussian-splatting.git --recursive
  2. Step 2 — Create the environment

    Build the conda environment from the repo file.

    conda env create --file environment.yml
    conda activate gaussian_splatting
  3. Step 3 — Train on a scene

    Train from an SfM dataset directory; see the README for the full command and options.

    python train.py -s <path to COLMAP or SfM dataset>
  4. Step 4 — Render the trained scene

    Generate renderings from the trained model with the render script.

    python render.py -m <path to trained model>
// cas d'usage

Ce que vous pouvez créer

  • Rebuild a real place in 3D from a set of photos
  • Render novel views of a scene in real time
  • Learn how radiance fields work from the reference code
  • Benchmark new 3DGS methods against the original

Close neighbours on the AI 3D shelf: Nerfstudio — the plug-and-play studio for NeRFs and Gaussian, and 4d-gaussian-splatting — ICLR 2024] Live Photorealistic Dynamic Scene. The full shelf is the AI 3D tools in the catalogue.

// faq

Questions fréquentes

What is 3D Gaussian Splatting?

A way to rebuild a 3D scene from photos as millions of 3D Gaussians, then render new viewpoints of it in real time — the SIGGRAPH 2023 paper from Inria and MPI.

Can I use it commercially?

Not without permission: the licence allows research and evaluation use only, and commercial use needs prior explicit consent from Inria.

What hardware do I need?

A CUDA-ready GPU (compute capability 7.0+) — 24GB of VRAM for paper-quality training; smaller configs are covered in the README FAQ.

How is it different from NeRF?

Same goal — novel-view synthesis — but much faster: real-time rendering at 1080p instead of seconds per frame.

Where do I start?

Clone with --recursive, create the conda environment, and follow the step-by-step tutorial linked in the README.

// continuez l'exploration

Outils similaires

IA 3D

Nerfstudio

Nerfstudio — the plug-and-play studio for NeRFs and Gaussian splatting: turn photos of a real scene into explorable 3D, with a modular API and viewer, Apache-2.0

★ 12,1 k étoilesApache-2.0
Voir le guide →
IA 3D

4d-gaussian-splatting

ICLR 2024] Live Photorealistic Dynamic Scene Representation and Rendering.

★ 1,0 k étoilesMIT
Voir le guide →
IA 3D

Gaussian-LIC

Real-time LiDAR-inertial-camera Gaussian Splatting SLAM.

★ 658 étoilesCustom
Voir le guide →
IA 3D

GS-SDF

LiDAR-augmented Gaussian Splatting plus neural SDF, in real time.

★ 535 étoilesGPL-2.0
Voir le guide →
IA 3D

MILo

Mesh-in-the-loop Gaussian Splatting from a SIGGRAPH Asia paper.

★ 528 étoilesNOASSERTION
Voir le guide →
IA 3D

QuestRoomScan

Real-time 3D room reconstruction on Meta Quest 3.

★ 70 étoilesNOASSERTION
Voir le guide →
// alternatives

Alternatives en IA 3D

Les autres projets de la catégorie IA 3D avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si 3D Gaussian Splatting ne vous convient pas.

  • mcp-for-blender★ 30,2 k

    Control Blender with natural language: an MCP plugin that lets any LLM model, light and animate in 3D

  • editor★ 24,7 k

    Pascal Editor: an open-source 3D architectural editor with MCP tools for humans and AI agents

  • text-to-cad★ 18,4 k

    Give your AI agent CAD superpowers - generate real STEP/STL models from text

  • img2threejs★ 17,7 k

    Turn a reference image into a procedural, animation-ready Three.js model - as code

  • SolidCraft★ 16,4 k

    Open-source parametric 3D CAD in pure Rust — desktop, browser, and an MCP server for AI agents

// plus en ai-3d

Plus en IA 3D

Projets de la catégorie IA 3D proches dans le catalogue, les plus proches en étoiles de 3D Gaussian Splatting — continuez à explorer de part et d'autre.

  • editor★ 24,7 k

    Pascal Editor: an open-source 3D architectural editor with MCP tools for humans and AI agents

  • text-to-cad★ 18,4 k

    Give your AI agent CAD superpowers - generate real STEP/STL models from text

  • mcp-for-blender★ 30,2 k

    Control Blender with natural language: an MCP plugin that lets any LLM model, light and animate in 3D

  • img2threejs★ 17,7 k

    Turn a reference image into a procedural, animation-ready Three.js model - as code

  • NURBGen★ 34

    Text-to-CAD: generate NURBS models from plain language.

  • SolidCraft★ 16,4 k

    Open-source parametric 3D CAD in pure Rust — desktop, browser, and an MCP server for AI agents

Obtenir 3D Gaussian Splatting

Consultez le code source, mettez une étoile au dépôt et commencez à créer.