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

3D Gaussian Splatting

3D Gaussian Splatting ist ein Projekt aus der Kategorie 3D-KI von graphdeco-inria (graphdeco-inria/gaussian-splatting auf GitHub). Es hat 24.460 Sterne auf GitHub und 3.494 Forks, wird unter den Bedingungen «Research-only» veröffentlicht und wurde zuletzt am 17. Oktober 2025 auf GitHub aktualisiert.

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

★ 24,5 Tsd. Sterne⑂ 3,5 Tsd. ForksResearch-onlyaktualisiert Okt 2025
▦ Visual — das README dieses Projekts enthält keinen einbettbaren Screenshot,
darum hier ein Platzhalter. Die Anleitung unten ist trotzdem vollständig.
// projektdaten

Projektdaten

GitHub-Sterne
24.460
Forks
3.494
Lizenz
Research-only
Zuletzt auf GitHub aktualisiert
17. Oktober 2025
Kategorie
3D-KI
Eintragstyp
Vollständige Installationsanleitung
Offizielle Website
Project page
// so funktioniert es

So funktioniert es

  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.

// funktionen

Warum es so beliebt ist

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.

// selbst ausführen

Führe es selbst aus

  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>
// anwendungsfälle

Was du damit bauen kannst

  • 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.

// häufige fragen

Häufige Fragen

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.

// weiter entdecken

Ähnliche Tools

3D-KI

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 Tsd. SterneApache-2.0
Anleitung ansehen →
3D-KI

4d-gaussian-splatting

ICLR 2024] Live Photorealistic Dynamic Scene Representation and Rendering.

★ 1,0 Tsd. SterneMIT
Anleitung ansehen →
3D-KI

Gaussian-LIC

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

★ 658 SterneCustom
Anleitung ansehen →
3D-KI

GS-SDF

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

★ 535 SterneGPL-2.0
Anleitung ansehen →
3D-KI

MILo

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

★ 528 SterneNOASSERTION
Anleitung ansehen →
3D-KI

QuestRoomScan

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

★ 70 SterneNOASSERTION
Anleitung ansehen →
// alternativen

Alternativen im Bereich 3D-KI

Die anderen Projekte der Kategorie 3D-KI mit den meisten Sternen im LibreAI-Katalog — die realistische Auswahl, falls 3D Gaussian Splatting nicht das Richtige ist.

  • mcp-for-blender★ 30,2 Tsd.

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

  • editor★ 24,7 Tsd.

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

  • text-to-cad★ 18,4 Tsd.

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

  • img2threejs★ 17,7 Tsd.

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

  • SolidCraft★ 16,4 Tsd.

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

// mehr in ai-3d

Mehr in 3D-KI

Verwandte Projekte der Kategorie 3D-KI im Katalog, die 3D Gaussian Splatting bei den Sternen am nächsten stehen — zum Weiterstöbern auf beiden Seiten.

  • editor★ 24,7 Tsd.

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

  • text-to-cad★ 18,4 Tsd.

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

  • mcp-for-blender★ 30,2 Tsd.

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

  • img2threejs★ 17,7 Tsd.

    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 Tsd.

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

Hol dir 3D Gaussian Splatting

Sieh dir den Quellcode an, gib dem Repository einen Stern und leg los.