{"id":13601732,"url":"https://github.com/nerfstudio-project/gsplat","last_synced_at":"2025-05-12T13:14:53.369Z","repository":{"id":199919871,"uuid":"683223775","full_name":"nerfstudio-project/gsplat","owner":"nerfstudio-project","description":"CUDA accelerated rasterization of gaussian splatting","archived":false,"fork":false,"pushed_at":"2025-05-12T10:49:52.000Z","size":122312,"stargazers_count":2943,"open_issues_count":185,"forks_count":425,"subscribers_count":53,"default_branch":"main","last_synced_at":"2025-05-12T13:14:40.468Z","etag":null,"topics":["gaussian-splatting"],"latest_commit_sha":null,"homepage":"https://docs.gsplat.studio/","language":"Cuda","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/nerfstudio-project.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.bib","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-08-25T22:48:24.000Z","updated_at":"2025-05-12T12:42:10.000Z","dependencies_parsed_at":null,"dependency_job_id":"5b422a4f-0323-4de3-9524-863688bf900f","html_url":"https://github.com/nerfstudio-project/gsplat","commit_stats":null,"previous_names":["nerfstudio-project/gsplat"],"tags_count":24,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nerfstudio-project%2Fgsplat","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nerfstudio-project%2Fgsplat/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nerfstudio-project%2Fgsplat/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nerfstudio-project%2Fgsplat/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nerfstudio-project","download_url":"https://codeload.github.com/nerfstudio-project/gsplat/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253745196,"owners_count":21957319,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["gaussian-splatting"],"created_at":"2024-08-01T18:01:07.244Z","updated_at":"2025-05-12T13:14:53.350Z","avatar_url":"https://github.com/nerfstudio-project.png","language":"Cuda","funding_links":[],"categories":["6. 3D Gaussian Viewers","3D视觉生成重建","Repos","Cuda","Open Source Implementations","Training","2023:","6. Generative Media Tools","Tools, Pipeline \u0026 Utilities","Gaussian splatting software"],"sub_categories":["Training","资源传输下载","Unofficial Implementations","Diffusion 3D Gaussian Splatting:","5. Mathematical Supplement for the gsplat Library","Photogrammetry \u0026 3D Scanning"],"readme":"# gsplat\n\n[![Core Tests.](https://github.com/nerfstudio-project/gsplat/actions/workflows/core_tests.yml/badge.svg?branch=main)](https://github.com/nerfstudio-project/gsplat/actions/workflows/core_tests.yml)\n[![Docs](https://github.com/nerfstudio-project/gsplat/actions/workflows/doc.yml/badge.svg?branch=main)](https://github.com/nerfstudio-project/gsplat/actions/workflows/doc.yml)\n\n[http://www.gsplat.studio/](http://www.gsplat.studio/)\n\ngsplat 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](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/), but we’ve made gsplat even faster, more memory efficient, and with a growing list of new features! \n\n\u003cdiv align=\"center\"\u003e\n  \u003cvideo src=\"https://github.com/nerfstudio-project/gsplat/assets/10151885/64c2e9ca-a9a6-4c7e-8d6f-47eeacd15159\" width=\"100%\" /\u003e\n\u003c/div\u003e\n\n## News\n\n[April 2025] [NVIDIA 3DGUT](https://research.nvidia.com/labs/toronto-ai/3DGUT/) is now integrated in gsplat! Checkout [here](docs/3dgut.md) for more details.\n\n## Installation\n\n**Dependence**: Please install [Pytorch](https://pytorch.org/get-started/locally/) first.\n\nThe easiest way is to install from PyPI. In this way it will build the CUDA code **on the first run** (JIT).\n\n```bash\npip install gsplat\n```\n\nAlternatively you can install gsplat from source. In this way it will build the CUDA code during installation.\n\n```bash\npip install git+https://github.com/nerfstudio-project/gsplat.git\n```\n\nWe also provide [pre-compiled wheels](https://docs.gsplat.studio/whl) 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](https://github.com/nerfstudio-project/gsplat/blob/6022cf45a19ee307803aaf1f19d407befad2a033/setup.py#L115). For example, to install gsplat for pytorch 2.0 and cuda 11.8 you can run\n```\npip install ninja numpy jaxtyping rich\npip install gsplat --index-url https://docs.gsplat.studio/whl/pt20cu118\n```\n\nTo build gsplat from source on Windows, please check [this instruction](docs/INSTALL_WIN.md).\n\n## Evaluation\n\nThis 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](https://docs.gsplat.studio/main/tests/eval.html).\n\n```bash\ncd examples\npip install -r requirements.txt\n# download mipnerf_360 benchmark data\npython datasets/download_dataset.py\n# run batch evaluation\nbash benchmarks/basic.sh\n```\n\n## Examples\n\nWe provide a set of examples to get you started! Below you can find the details about\nthe examples (requires to install some exta dependencies via `pip install -r examples/requirements.txt`)\n\n- [Train a 3D Gaussian splatting model on a COLMAP capture.](https://docs.gsplat.studio/main/examples/colmap.html)\n- [Fit a 2D image with 3D Gaussians.](https://docs.gsplat.studio/main/examples/image.html)\n- [Render a large scene in real-time.](https://docs.gsplat.studio/main/examples/large_scale.html)\n\n\n## Development and Contribution\n\nThis 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.\n\nThis project is developed by the following wonderful contributors (unordered):\n\n- [Angjoo Kanazawa](https://people.eecs.berkeley.edu/~kanazawa/) (UC Berkeley): Mentor of the project.\n- [Matthew Tancik](https://www.matthewtancik.com/about-me) (Luma AI): Mentor of the project.\n- [Vickie Ye](https://people.eecs.berkeley.edu/~vye/) (UC Berkeley): Project lead. v0.1 lead.\n- [Matias Turkulainen](https://maturk.github.io/) (Aalto University): Core developer.\n- [Ruilong Li](https://www.liruilong.cn/) (UC Berkeley): Core developer. v1.0 lead.\n- [Justin Kerr](https://kerrj.github.io/) (UC Berkeley): Core developer.\n- [Brent Yi](https://github.com/brentyi) (UC Berkeley): Core developer.\n- [Zhuoyang Pan](https://panzhy.com/) (ShanghaiTech University): Core developer.\n- [Jianbo Ye](http://www.jianboye.org/) (Amazon): Core developer.\n\nWe also have a white paper with about the project with benchmarking and mathematical supplement with conventions and derivations, available [here](https://arxiv.org/abs/2409.06765). If you find this library useful in your projects or papers, please consider citing:\n\n```\n@article{ye2025gsplat,\n  title={gsplat: An open-source library for Gaussian splatting},\n  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},\n  journal={Journal of Machine Learning Research},\n  volume={26},\n  number={34},\n  pages={1--17},\n  year={2025}\n}\n```\n\nWe 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](docs/DEV.md) for more info about development.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnerfstudio-project%2Fgsplat","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnerfstudio-project%2Fgsplat","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnerfstudio-project%2Fgsplat/lists"}