gsplat
CUDA accelerated rasterization of gaussian splatting
Science Score: 64.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
✓Committers with academic emails
5 of 84 committers (6.0%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (14.5%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
CUDA accelerated rasterization of gaussian splatting
Basic Info
- Host: GitHub
- Owner: nerfstudio-project
- License: apache-2.0
- Language: Cuda
- Default Branch: main
- Homepage: https://docs.gsplat.studio/
- Size: 130 MB
Statistics
- Stars: 3,466
- Watchers: 53
- Forks: 522
- Open Issues: 236
- Releases: 25
Topics
Metadata Files
README.md
gsplat
gsplat is an open-source library for CUDA accelerated rasterization of gaussians with python bindings. It is inspired by the SIGGRAPH paper 3D Gaussian Splatting for Real-Time Rendering of Radiance Fields, but we’ve made gsplat even faster, more memory efficient, and with a growing list of new features!
News
[May 2025] Arbitrary batching (over multiple scenes and multiple viewpoints) is supported now!! Checkout here for more details! Kudos to Junchen Liu.
[May 2025] Jonathan Stephens makes a great tutorial video for Windows users on how to install gsplat and get start with 3DGUT.
[April 2025] NVIDIA 3DGUT is now integrated in gsplat! Checkout here for more details. [NVIDIA Tech Blog] [NVIDIA Sweepstakes]
Installation
Dependence: Please install Pytorch first.
The easiest way is to install from PyPI. In this way it will build the CUDA code on the first run (JIT).
bash
pip install gsplat
Alternatively you can install gsplat from source. In this way it will build the CUDA code during installation.
bash
pip install git+https://github.com/nerfstudio-project/gsplat.git
We also provide pre-compiled wheels for both linux and windows on certain python-torch-CUDA combinations (please check first which versions are supported). Note this way you would have to manually install gsplat's dependencies. For example, to install gsplat for pytorch 2.0 and cuda 11.8 you can run
pip install ninja numpy jaxtyping rich
pip install gsplat --index-url https://docs.gsplat.studio/whl/pt20cu118
To build gsplat from source on Windows, please check this instruction.
Evaluation
This repo comes with a standalone script that reproduces the official Gaussian Splatting with exactly the same performance on PSNR, SSIM, LPIPS, and converged number of Gaussians. Powered by gsplat’s efficient CUDA implementation, the training takes up to 4x less GPU memory with up to 15% less time to finish than the official implementation. Full report can be found here.
```bash cd examples pip install -r requirements.txt
download mipnerf_360 benchmark data
python datasets/download_dataset.py
run batch evaluation
bash benchmarks/basic.sh ```
Examples
We provide a set of examples to get you started! Below you can find the details about
the examples (requires to install some exta dependencies via pip install -r examples/requirements.txt)
- Train a 3D Gaussian splatting model on a COLMAP capture.
- Fit a 2D image with 3D Gaussians.
- Render a large scene in real-time.
Development and Contribution
This repository was born from the curiosity of people on the Nerfstudio team trying to understand a new rendering technique. We welcome contributions of any kind and are open to feedback, bug-reports, and improvements to help expand the capabilities of this software.
This project is developed by the following wonderful contributors (unordered):
- Angjoo Kanazawa (UC Berkeley): Mentor of the project.
- Matthew Tancik (Luma AI): Mentor of the project.
- Vickie Ye (UC Berkeley): Project lead. v0.1 lead.
- Matias Turkulainen (Aalto University): Core developer.
- Ruilong Li (UC Berkeley): Core developer. v1.0 lead.
- Justin Kerr (UC Berkeley): Core developer.
- Brent Yi (UC Berkeley): Core developer.
- Zhuoyang Pan (ShanghaiTech University): Core developer.
- Jianbo Ye (Amazon): Core developer.
We also have a white paper with about the project with benchmarking and mathematical supplement with conventions and derivations, available here. If you find this library useful in your projects or papers, please consider citing:
@article{ye2025gsplat,
title={gsplat: An open-source library for Gaussian splatting},
author={Ye, Vickie and Li, Ruilong and Kerr, Justin and Turkulainen, Matias and Yi, Brent and Pan, Zhuoyang and Seiskari, Otto and Ye, Jianbo and Hu, Jeffrey and Tancik, Matthew and Angjoo Kanazawa},
journal={Journal of Machine Learning Research},
volume={26},
number={34},
pages={1--17},
year={2025}
}
We welcome contributions of any kind and are open to feedback, bug-reports, and improvements to help expand the capabilities of this software. Please check docs/DEV.md for more info about development.
Owner
- Name: nerfstudio
- Login: nerfstudio-project
- Kind: organization
- Location: United States of America
- Website: www.nerf.studio
- Repositories: 6
- Profile: https://github.com/nerfstudio-project
nerfstudio is an open-source project developed at UC Berkeley, led by students from the Kanazawa group and other collaborators
Citation (CITATION.bib)
@article{ye2024gsplatopensourcelibrarygaussian,
title={gsplat: An Open-Source Library for {Gaussian} Splatting},
author={Vickie Ye and Ruilong Li and Justin Kerr and Matias Turkulainen and Brent Yi and Zhuoyang Pan and Otto Seiskari and Jianbo Ye and Jeffrey Hu and Matthew Tancik and Angjoo Kanazawa},
year={2024},
eprint={2409.06765},
journal={arXiv preprint arXiv:2409.06765},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2409.06765},
}
Committers
Last synced: 9 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Ruilong Li(李瑞龙) | r****4@g****m | 122 |
| Vickie Ye | v****6@g****m | 91 |
| maturk | m****n@g****m | 61 |
| Ruilong Li | 3****3@q****m | 35 |
| Brent Yi | y****h@g****m | 17 |
| Justin Kerr | j****r@g****m | 17 |
| Zhuoyang | z****n@o****m | 14 |
| J.Y | 1****e | 9 |
| Jeffrey Hu | h****4@g****m | 6 |
| Francis Williams | f****s | 5 |
| Vitchyr Pong | v****r@g****m | 5 |
| janusch | 3****F | 5 |
| Jonathan | j****v@b****u | 4 |
| JC | l****4@g****m | 4 |
| akanazawa | a****a | 3 |
| Rahul Goel | 5****l | 3 |
| Otto Seiskari | o****i@g****m | 3 |
| Ikko Eltociear Ashimine | e****r@g****m | 3 |
| FantasticOven2 | 9****2 | 3 |
| Christian Richardt | c****n@r****e | 3 |
| Congrong Xu | 5****2 | 2 |
| Heng | 3****g | 2 |
| Jenia Golbstein | j****a@n****m | 2 |
| MotivaCG | v****r@m****m | 2 |
| Desmond Liu | l****5@g****m | 1 |
| DylanWaken | 1****n | 1 |
| Forrest Iandola | f****a@g****m | 1 |
| Frank_Liu | l****6@1****m | 1 |
| Georg Hess | h****9@g****m | 1 |
| Hang | h****7@g****m | 1 |
| and 54 more... | ||
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 397
- Total pull requests: 437
- Average time to close issues: 26 days
- Average time to close pull requests: 11 days
- Total issue authors: 301
- Total pull request authors: 120
- Average comments per issue: 1.36
- Average comments per pull request: 1.33
- Merged pull requests: 309
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 233
- Pull requests: 242
- Average time to close issues: 15 days
- Average time to close pull requests: 6 days
- Issue authors: 193
- Pull request authors: 64
- Average comments per issue: 0.9
- Average comments per pull request: 1.04
- Merged pull requests: 169
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- martinResearch (7)
- MasahiroOgawa (6)
- Metro1998 (5)
- LaFeuilleMorte (5)
- canxerian (5)
- zerolover (4)
- rkakash59 (4)
- abrahamezzeddine (3)
- scott198510 (3)
- ichsan2895 (3)
- kwea123 (3)
- vincentwoo (3)
- NeutrinoLiu (3)
- insomniaaac (3)
- InFistLee (3)
Pull Request Authors
- liruilong940607 (143)
- maturk (18)
- MrNeRF (14)
- kerrj (10)
- RongLiu-Leo (10)
- vye16 (10)
- jb-ye (10)
- jefequien (9)
- fwilliams (7)
- FantasticOven2 (7)
- JunchenLiu77 (7)
- zerolover (7)
- martinResearch (6)
- brentyi (5)
- Golbstein (4)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 1
-
Total downloads:
- pypi 29,596 last-month
- Total dependent packages: 1
- Total dependent repositories: 1
- Total versions: 26
- Total maintainers: 3
pypi.org: gsplat
Python package for differentiable rasterization of gaussians
- Homepage: https://github.com/nerfstudio-project/gsplat
- Documentation: https://gsplat.readthedocs.io/
- License: apache-2.0
-
Latest release: 1.5.3
published 8 months ago