{"id":18600781,"url":"https://github.com/autonomousvision/mip-splatting","last_synced_at":"2025-05-14T21:06:22.500Z","repository":{"id":209504458,"uuid":"724227496","full_name":"autonomousvision/mip-splatting","owner":"autonomousvision","description":"[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting","archived":false,"fork":false,"pushed_at":"2024-12-17T10:42:50.000Z","size":21660,"stargazers_count":1231,"open_issues_count":31,"forks_count":87,"subscribers_count":21,"default_branch":"main","last_synced_at":"2025-04-13T18:44:33.001Z","etag":null,"topics":["3d-reconstruction","anti-aliasing","guassian-splatting","nerf","novel-view-synthesis"],"latest_commit_sha":null,"homepage":"https://niujinshuchong.github.io/mip-splatting/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/autonomousvision.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","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":"2023-11-27T16:49:03.000Z","updated_at":"2025-04-11T21:41:35.000Z","dependencies_parsed_at":"2024-12-27T07:01:01.160Z","dependency_job_id":null,"html_url":"https://github.com/autonomousvision/mip-splatting","commit_stats":{"total_commits":15,"total_committers":3,"mean_commits":5.0,"dds":0.1333333333333333,"last_synced_commit":"dda02ab5ecf45d6edb8c540d9bb65c7e451345a9"},"previous_names":["autonomousvision/mip-splatting"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autonomousvision%2Fmip-splatting","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autonomousvision%2Fmip-splatting/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autonomousvision%2Fmip-splatting/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autonomousvision%2Fmip-splatting/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/autonomousvision","download_url":"https://codeload.github.com/autonomousvision/mip-splatting/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254227611,"owners_count":22035669,"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":["3d-reconstruction","anti-aliasing","guassian-splatting","nerf","novel-view-synthesis"],"created_at":"2024-11-07T02:05:24.298Z","updated_at":"2025-05-14T21:06:17.482Z","avatar_url":"https://github.com/autonomousvision.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n\n  \u003ch1 align=\"center\"\u003eMip-Splatting: Alias-free 3D Gaussian Splatting\u003c/h1\u003e\n  \u003cp align=\"center\"\u003e\n    \u003ca href=\"https://niujinshuchong.github.io/\"\u003eZehao Yu\u003c/a\u003e\n    ·\n    \u003ca href=\"https://apchenstu.github.io/\"\u003eAnpei Chen\u003c/a\u003e\n    ·\n    \u003ca href=\"https://github.com/hbb1\"\u003eBinbin Huang\u003c/a\u003e\n    ·\n    \u003ca href=\"https://tsattler.github.io/\"\u003eTorsten Sattler\u003c/a\u003e\n    ·\n    \u003ca href=\"http://www.cvlibs.net/\"\u003eAndreas Geiger\u003c/a\u003e\n\n  \u003c/p\u003e\n  \u003ch2 align=\"center\"\u003eCVPR 2024 Best Student Paper\u003c/h2\u003e\n\n  \u003ch3 align=\"center\"\u003e\u003ca href=\"https://drive.google.com/file/d/1Q7KgGbynzcIEyFJV1I17HgrYz6xrOwRJ/view?usp=sharing\"\u003ePaper\u003c/a\u003e | \u003ca href=\"https://arxiv.org/pdf/2311.16493.pdf\"\u003earXiv\u003c/a\u003e | \u003ca href=\"https://niujinshuchong.github.io/mip-splatting/\"\u003eProject Page\u003c/a\u003e  | \u003ca href=\"https://niujinshuchong.github.io/mip-splatting-demo/\"\u003eOnline Viewer\u003c/a\u003e \u003c/h3\u003e\n  \u003cdiv align=\"center\"\u003e\u003c/div\u003e\n\u003c/p\u003e\n\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"\"\u003e\n    \u003cimg src=\"./media/bicycle_3dgs_vs_ours.gif\" alt=\"Logo\" width=\"95%\"\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\nWe introduce a 3D smoothing filter and a 2D Mip filter for 3D Gaussian Splatting (3DGS), eliminating multiple artifacts and achieving alias-free renderings.  \n\u003c/p\u003e\n\u003cbr\u003e\n\n# Update\nWe integrated an improved densification metric proposed in [Gaussian Opacity Fields](https://niujinshuchong.github.io/gaussian-opacity-fields/), which significantly improves the novel view synthesis results, please check the [paper](https://arxiv.org/pdf/2404.10772.pdf) for details. Please download the lastest code and reinstall `diff-gaussian-rasterization` to try it out. \n\n# Installation\nClone the repository and create an anaconda environment using\n```\ngit clone git@github.com:autonomousvision/mip-splatting.git\ncd mip-splatting\n\nconda create -y -n mip-splatting python=3.8\nconda activate mip-splatting\n\npip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 -f https://download.pytorch.org/whl/torch_stable.html\nconda install cudatoolkit-dev=11.3 -c conda-forge\n\npip install -r requirements.txt\n\npip install submodules/diff-gaussian-rasterization\npip install submodules/simple-knn/\n```\n\n# Dataset\n## Blender Dataset\nPlease download and unzip nerf_synthetic.zip from the [NeRF's official Google Drive](https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1). Then generate multi-scale blender dataset with\n```\npython convert_blender_data.py --blender_dir nerf_synthetic/ --out_dir multi-scale\n```\n\n## Mip-NeRF 360 Dataset\nPlease download the data from the [Mip-NeRF 360](https://jonbarron.info/mipnerf360/) and request the authors for the treehill and flowers scenes.\n\n# Training and Evaluation\n```\n# single-scale training and multi-scale testing on NeRF-synthetic dataset\npython scripts/run_nerf_synthetic_stmt.py \n\n# multi-scale training and multi-scale testing on NeRF-synthetic dataset\npython scripts/run_nerf_synthetic_mtmt.py \n\n# single-scale training and single-scale testing on the mip-nerf 360 dataset\npython scripts/run_mipnerf360.py \n\n# single-scale training and multi-scale testing on the mip-nerf 360 dataset\npython scripts/run_mipnerf360_stmt.py \n```\n\n# Online viewer\nAfter training, you can fuse the 3D smoothing filter to the Gaussian parameters with\n```\npython create_fused_ply.py -m {model_dir}/{scene} --output_ply fused/{scene}_fused.ply\"\n```\nThen use our [online viewer](https://niujinshuchong.github.io/mip-splatting-demo) to visualize the trained model.\n\n# Acknowledgements\nThis project is built upon [3DGS](https://github.com/graphdeco-inria/gaussian-splatting). Please follow the license of 3DGS. We thank all the authors for their great work and repos. \n\n# Citation\nIf you find our code or paper useful, please cite\n```bibtex\n@InProceedings{Yu2024MipSplatting,\n    author    = {Yu, Zehao and Chen, Anpei and Huang, Binbin and Sattler, Torsten and Geiger, Andreas},\n    title     = {Mip-Splatting: Alias-free 3D Gaussian Splatting},\n    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},\n    month     = {June},\n    year      = {2024},\n    pages     = {19447-19456}\n}\n```\nIf you find our improved densification metric useful, please kindly cite\n```\n@article{Yu2024GOF,\n  author    = {Yu, Zehao and Sattler, Torsten and Geiger, Andreas},\n  title     = {Gaussian Opacity Fields: Efficient High-quality Compact Surface Reconstruction in Unbounded Scenes},\n  journal   = {arXiv:2404.10772},\n  year      = {2024},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fautonomousvision%2Fmip-splatting","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fautonomousvision%2Fmip-splatting","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fautonomousvision%2Fmip-splatting/lists"}