Gaussian Splatting (3DGS): 3D Generator — What It Does and What You Need to Run It

3D Gaussian Splatting (3DGS) is a 3D generator that reconstructs a scene from a set of photographs and lets you view it in real time. The tool was created by the Inria and MPII research groups and is distributed as open source.

What it does

The authors describe the project as the reference implementation of the "3D Gaussian Splatting for Real-Time Radiance Field Rendering" method. The tool trains on input images and builds a scene representation that can then be rendered at high speed. The repository lists the tags: computer-graphics, computer-vision and radiance-field.

What you need to run it

• Platform: as described by the author, CUDA is required. The optimizer uses PyTorch and CUDA extensions in a Python environment.
• VRAM: as described by the author, training the model to the quality claimed in the paper requires 24 GB of VRAM. The authors do not state memory requirements for inference.
• Code language: Python.
• Code license: Gaussian-Splatting License: non-commercial research only.
• Repository: github.com/graphdeco-inria/gaussian-splatting
• Project website: https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/

Who it suits

The tool is aimed at researchers and developers in computer graphics and computer vision who are ready to work with Python code and have access to a CUDA-capable GPU with a large amount of VRAM. Training to the quality described in the original paper requires 24 GB of VRAM, which limits the range of available consumer graphics cards. It is not a good fit for those looking for a ready-made application with a graphical interface, or for those who do not have suitable hardware.

The repository code was last updated on October 17, 2025, and the repository itself was created in July 2023. The Gaussian-Splatting License permits free use, modification and distribution for non-commercial research purposes only; commercial use requires the prior explicit consent of the licensors.