{"id":19137475,"url":"https://github.com/dsaurus/threestudio-3dgs","last_synced_at":"2025-08-20T02:32:41.883Z","repository":{"id":210255892,"uuid":"725697307","full_name":"DSaurus/threestudio-3dgs","owner":"DSaurus","description":"3D Gaussian Splatting extension of threestudio.","archived":false,"fork":false,"pushed_at":"2024-03-20T15:23:34.000Z","size":930,"stargazers_count":175,"open_issues_count":13,"forks_count":14,"subscribers_count":7,"default_branch":"main","last_synced_at":"2024-12-11T12:24:44.149Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DSaurus.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-11-30T17:26:01.000Z","updated_at":"2024-11-30T10:49:08.000Z","dependencies_parsed_at":"2024-03-20T16:52:05.090Z","dependency_job_id":null,"html_url":"https://github.com/DSaurus/threestudio-3dgs","commit_stats":null,"previous_names":["dsaurus/threestudio-3dgs"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DSaurus%2Fthreestudio-3dgs","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DSaurus%2Fthreestudio-3dgs/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DSaurus%2Fthreestudio-3dgs/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DSaurus%2Fthreestudio-3dgs/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DSaurus","download_url":"https://codeload.github.com/DSaurus/threestudio-3dgs/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":230388130,"owners_count":18217755,"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":[],"created_at":"2024-11-09T06:38:32.070Z","updated_at":"2024-12-19T06:08:53.321Z","avatar_url":"https://github.com/DSaurus.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# threestudio-3dgs\n\u003cimg src=\"https://github.com/DSaurus/threestudio-3dgs/assets/24589363/55874a57-cff1-4e83-a006-76585bcd3b76\" width=\"\" height=\"128\"\u003e\n\n\u003cimg src=\"https://github.com/DSaurus/threestudio-3dgs/assets/24589363/505f35e5-b160-4c12-92dc-03482404ef5e\" width=\"\" height=\"128\"\u003e\n\n\u003cimg src=\"https://github.com/DSaurus/threestudio-3dgs/assets/24589363/a1041f0d-a56f-4f7f-adc3-1e99c2d81098\" width=\"\" height=\"128\"\u003e\n\n\u003cimg src=\"https://github.com/DSaurus/threestudio-3dgs/assets/24589363/f524524e-33aa-4701-9f0d-31cba23eaead\" width=\"\" height=\"128\"\u003e\n\nThe Gaussian Splatting extension for threestudio. This extension is writen by [Ruizhi Shao](https://github.com/DSaurus) and [Youtian Lin](https://github.com/Linyou). To use it, please install [threestudio](https://github.com/threestudio-project/threestudio) first and then install this extension in threestudio `custom` directory.\n\n## Advanced Gaussian Splatting Installation (Recommend)\n```\ncd custom\ngit clone https://github.com/DSaurus/threestudio-3dgs.git\ncd threestudio-3dgs\ngit clone --recursive https://github.com/ashawkey/diff-gaussian-rasterization\ngit clone https://github.com/DSaurus/simple-knn.git\npip install ./diff-gaussian-rasterization\npip install ./simple-knn\n```\n\n## Native Gaussian Splatting Installation\n```\ncd custom\ngit clone https://github.com/DSaurus/threestudio-3dgs.git\ncd threestudio-3dgs\ngit clone git@github.com:graphdeco-inria/gaussian-splatting.git --recursive\ncd gaussian-splatting/submodules\npython -m pip install diff-gaussian-rasterization/.\npython -m pip install simple-knn/\n\n# If you want to export mesh, please install pymeshlab\npip install pymeshlab\n```\n\n\n## Quick Start\n```\n# Native Gaussian Splatting + SDS Loss\npython launch.py --config custom/threestudio-3dgs/configs/gaussian_splatting.yaml  --train --gpu 0 system.prompt_processor.prompt=\"a delicious hamburger\"\n\n# Advanced Gaussian Splatting with background + SDS Loss\npython launch.py --config custom/threestudio-3dgs/configs/gaussian_splatting_background.yaml  --train --gpu 0 system.prompt_processor.prompt=\"a delicious hamburger\"\n\n# Advanced Gaussian Splatting with background and shading + SDS Loss\npython launch.py --config custom/threestudio-3dgs/configs/gaussian_splatting_shading.yaml  --train --gpu 0 system.prompt_processor.prompt=\"a delicious hamburger\"\n```\n\n## Gaussian Splatting + MVDream\nPlease first install [MVDream extension](https://github.com/DSaurus/threestudio-mvdream), then you can run the following script:\n```\n# Advanced Gaussian Splatting with background and shading + MVDream\npython launch.py --config custom/threestudio-3dgs/configs/gaussian_splatting_mvdream.yaml  --train --gpu 0 system.prompt_processor.prompt=\"an astronaut riding a horse\"\n```\n\n## Gaussian Splatting + Zero-123\n```\n# Advanced Gaussian Splatting + Zero-123\npython launch.py --config custom/threestudio-3dgs/configs/gaussian_splatting_zero123.yaml --train --gpu 0 data.image_path=./load/images/anya_front_rgba.png\n```\n\n## Resume from checkpoints\n```\n# resume training from the last checkpoint, you may replace last.ckpt with any other checkpoints\npython launch.py --config path/to/trial/dir/configs/parsed.yaml --train --gpu 0 resume=path/to/trial/dir/ckpts/last.ckpt\n```\n\n## Load from PLY\n```\n# load from Gaussian Splatting ply file\npython launch.py --config custom/threestudio-3dgs/configs/gaussian_splatting.yaml  --train --gpu 0 system.prompt_processor.prompt=\"a delicious hamburger\" system.geometry.geometry_conver_from=path/to/poinc_cloud.ply\n\n# only load points position and color from ply file\npython launch.py --config custom/threestudio-3dgs/configs/gaussian_splatting.yaml  --train --gpu 0 system.prompt_processor.prompt=\"a delicious hamburger\" system.geometry.geometry_conver_from=path/to/poinc_cloud.ply system.geometry.load_ply_only_vertex=true\n```\n\nIf you want to use shap-e initialization, please install [threestudio-shap-e extension](https://github.com/DSaurus/threestudio-shap-e) first.\n```\n# load from shap-e initialization\npython launch.py --config custom/threestudio-3dgs/configs/gaussian_splatting.yaml  --train --gpu 0 system.prompt_processor.prompt=\"a delicious hamburger\" system.geometry.geometry_convert_from=\"shap-e:a delicious hamburger\"\n```\n\nIf you want to use LRM initialization, please install [threestudio-lrm extension](https://github.com/Adamdad/threestudio-lrm) first.\n```\n# load from lrm initialization\npython launch.py --config custom/threestudio-3dgs/configs/gaussian_splatting.yaml  --train --gpu 0 system.prompt_processor.prompt=\"a delicious hamburger\" system.geometry.geometry_convert_from=\"lrm:a delicious hamburger\"\n```\n\n## Export\nYou can use the following script to export Gaussian Splatting ply file and mesh obj.\n```\npython launch.py --config path/to/config --export --gpu 0 system.prompt_processor.prompt=\"a delicious hamburger\" resume=path/to/last.ckpt\n```\n\n## Citation\n```\n@Article{kerbl3Dgaussians,\n    author       = {Kerbl, Bernhard and Kopanas, Georgios and Leimk{\\\"u}hler, Thomas and Drettakis, George},\n    title        = {3D Gaussian Splatting for Real-Time Radiance Field Rendering},\n    journal      = {ACM Transactions on Graphics},\n    number       = {4},\n    volume       = {42},\n    month        = {July},\n    year         = {2023},\n    url          = {https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/}\n}\n```\n\n## Acknowledgement\nPlease also consider citing these work about 3D Gaussian Splatting generation. Their open-source code inspires this project..\n\n```\n@article{tang2023dreamgaussian,\n    title={DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation},\n    author={Tang, Jiaxiang and Ren, Jiawei and Zhou, Hang and Liu, Ziwei and Zeng, Gang},\n    journal={arXiv preprint arXiv:2309.16653},\n    year={2023}\n}\n```\n\n```\n@article{GaussianDreamer,\n    title={GaussianDreamer: Fast Generation from Text to 3D Gaussian Splatting with Point Cloud Priors},\n    author={Taoran Yi and Jiemin Fang and Guanjun Wu and Lingxi Xie and Xiaopeng Zhang and Wenyu Liu and Qi Tian and Xinggang Wang},\n    journal={arxiv:2310.08529},\n    year={2023}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdsaurus%2Fthreestudio-3dgs","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdsaurus%2Fthreestudio-3dgs","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdsaurus%2Fthreestudio-3dgs/lists"}