{"id":13444200,"url":"https://github.com/NVIDIAGameWorks/kaolin","last_synced_at":"2025-03-20T18:31:35.618Z","repository":{"id":37735312,"uuid":"221787282","full_name":"NVIDIAGameWorks/kaolin","owner":"NVIDIAGameWorks","description":"A PyTorch Library for Accelerating 3D Deep Learning Research","archived":false,"fork":false,"pushed_at":"2024-09-27T21:54:55.000Z","size":120198,"stargazers_count":4477,"open_issues_count":102,"forks_count":557,"subscribers_count":111,"default_branch":"master","last_synced_at":"2024-10-30T03:39:30.253Z","etag":null,"topics":["3d-deep-learning","artificial-intelligence","camera-api","cuda","differentiable-lighting","differentiable-rendering","neural-networks","pytorch","rasterization"],"latest_commit_sha":null,"homepage":"","language":"Python","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/NVIDIAGameWorks.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","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":"2019-11-14T21:09:40.000Z","updated_at":"2024-10-29T10:21:46.000Z","dependencies_parsed_at":"2023-02-17T22:30:28.720Z","dependency_job_id":"e1307c44-3fb1-4765-8161-4d285fb77abf","html_url":"https://github.com/NVIDIAGameWorks/kaolin","commit_stats":{"total_commits":345,"total_committers":33,"mean_commits":"10.454545454545455","dds":0.5565217391304348,"last_synced_commit":"7b3b46efb12ebaf1a339fe54fc14f56643b32f88"},"previous_names":[],"tags_count":14,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIAGameWorks%2Fkaolin","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIAGameWorks%2Fkaolin/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIAGameWorks%2Fkaolin/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIAGameWorks%2Fkaolin/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NVIDIAGameWorks","download_url":"https://codeload.github.com/NVIDIAGameWorks/kaolin/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244670200,"owners_count":20490938,"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-deep-learning","artificial-intelligence","camera-api","cuda","differentiable-lighting","differentiable-rendering","neural-networks","pytorch","rasterization"],"created_at":"2024-07-31T03:02:21.670Z","updated_at":"2025-03-20T18:31:35.612Z","avatar_url":"https://github.com/NVIDIAGameWorks.png","language":"Python","readme":"# Kaolin: A Pytorch Library for Accelerating 3D Deep Learning Research\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"assets/kaolin.png\"\u003e\n\u003c/p\u003e\n\n## Overview\nNVIDIA Kaolin library provides a PyTorch API for working with a variety of 3D representations and includes a growing collection of GPU-optimized operations such as modular differentiable rendering, fast conversions between representations, data loading, 3D checkpoints, differentiable camera API, differentiable lighting with spherical harmonics and spherical gaussians, powerful quadtree acceleration structure called Structured Point Clouds, interactive 3D visualizer for jupyter notebooks, convenient batched mesh container and more. Visit the [Kaolin Library Documentation](https://kaolin.readthedocs.io/en/latest/) to get started!\n\nNote that Kaolin library is part of the larger [NVIDIA Kaolin effort](https://developer.nvidia.com/kaolin) for 3D deep learning.\n\n## Installation and Getting Started\n\nStarting with v0.12.0, Kaolin supports installation with wheels:\n```\n# Replace TORCH_VERSION and CUDA_VERSION with your torch / cuda versions\npip install kaolin==0.17.0 -f https://nvidia-kaolin.s3.us-east-2.amazonaws.com/torch-{TORCH_VERSION}_cu{CUDA_VERSION}.html\n```\nFor example, to install kaolin 0.17.0 over torch 2.0.1 and cuda 11.8:\n```\npip install kaolin==0.17.0 -f https://nvidia-kaolin.s3.us-east-2.amazonaws.com/torch-2.0.1_cu118.html\n```\n\n## About the Latest Release (0.17.0)\n\nIn this version we added [sample_points_in_volume](https://kaolin.readthedocs.io/en/latest/modules/kaolin.ops.gaussian.html#kaolin.ops.gaussian.sample_points_in_volume) function used for \"densifying\" a gaussian splats, this can be used to improve [Physics simulation](https://kaolin.readthedocs.io/en/latest/modules/physics.html).\n\nWe further improved physics training and simulation using [NVIDIA Warp](https://github.com/NVIDIA/warp) on some of our functions. We also added support for transmittance in the GLTF loader.\n\n![](assets/no_densifier_small.gif) | ![](assets/with_densifier_small.gif)\n:---------------------------------:|:------------------------------------:\nWithout Densifier                  |  With Densifier\n\nCheck our updated tutorials:\n* [Use Simplicit's Easy API to Simulate a Mesh](https://github.com/NVIDIAGameWorks/kaolin/blob/master/examples/tutorial/physics/simplicits_easy_api.ipynb)\n* [Interact with a Physics Simulation](https://github.com/NVIDIAGameWorks/kaolin/blob/master/examples/tutorial/physics/simplicits_interactive.ipynb)\n* [Use Simplicit's Full-Feature API](https://github.com/NVIDIAGameWorks/kaolin/blob/master/examples/tutorial/physics/simplicits_low_level_api.ipynb)\n* [Simulate a Gaussian Splat](https://gitlab-master.nvidia.com/Toronto_DL_Lab/kaolin/-/blob/master/examples/tutorial/physics/simplicits_inria_splatting.ipynb)\n* [Simulate a Muscle Activation on a Musculoskeletal Mesh](https://gitlab-master.nvidia.com/Toronto_DL_Lab/kaolin/-/blob/master/examples/tutorial/physics/simplicits_muscle_activation.ipynb)\n\nSee [change logs](https://github.com/NVIDIAGameWorks/kaolin/releases/tag/v0.17.0) for details.\n\n## Contributing\n\nPlease review our [contribution guidelines](CONTRIBUTING.md).\n\n## External Projects using Kaolin\n\n* [NVIDIA Kaolin Wisp](https://github.com/NVIDIAGameWorks/kaolin-wisp):\n   * Use [Camera API](https://kaolin.readthedocs.io/en/latest/modules/kaolin.render.camera.html), [Structured Point Clouds](https://kaolin.readthedocs.io/en/latest/modules/kaolin.ops.spc.html) and its [rendering capabilities](https://kaolin.readthedocs.io/en/latest/modules/kaolin.render.spc.html)\n* [gradSim: Differentiable simulation for system identification and visuomotor control](https://github.com/gradsim/gradsim):\n   * Use [DIB-R rasterizer](https://kaolin.readthedocs.io/en/latest/modules/kaolin.render.mesh.html#kaolin.render.mesh.dibr_rasterization), [obj loader](https://kaolin.readthedocs.io/en/latest/modules/kaolin.io.obj.html#kaolin.io.obj.import_mesh) and [timelapse](https://kaolin.readthedocs.io/en/latest/modules/kaolin.visualize.html#kaolin.visualize.Timelapse)\n* [Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer](https://github.com/nv-tlabs/DIB-R-Single-Image-3D-Reconstruction/tree/2cfa689881145c8e0647ae8dd077e55b5a578658):\n   * Use [Kaolin's DIB-R rasterizer](https://kaolin.readthedocs.io/en/latest/modules/kaolin.render.mesh.html#kaolin.render.mesh.dibr_rasterization), [camera functions](https://kaolin.readthedocs.io/en/latest/modules/kaolin.render.camera.html) and [Timelapse](https://kaolin.readthedocs.io/en/latest/modules/kaolin.visualize.html#kaolin.visualize.Timelapse) for 3D checkpoints.\n* [Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Surfaces](https://github.com/nv-tlabs/nglod):\n    * Use [SPC](https://kaolin.readthedocs.io/en/latest/modules/kaolin.ops.spc.html) conversions and [ray-tracing](https://kaolin.readthedocs.io/en/latest/modules/kaolin.render.spc.html#kaolin.render.spc.unbatched_raytrace), yielding 30x memory and 3x training time reduction.\n* [Learning Deformable Tetrahedral Meshes for 3D Reconstruction](https://github.com/nv-tlabs/DefTet):\n    * Use [Kaolin's DefTet volumetric renderer](https://kaolin.readthedocs.io/en/latest/modules/kaolin.render.mesh.html#kaolin.render.mesh.deftet_sparse_render), [tetrahedral losses](https://kaolin.readthedocs.io/en/latest/modules/kaolin.metrics.tetmesh.html), [camera_functions](https://kaolin.readthedocs.io/en/latest/modules/kaolin.render.camera.html), [mesh operators and conversions](https://kaolin.readthedocs.io/en/latest/modules/kaolin.ops.html), [ShapeNet dataset](https://kaolin.readthedocs.io/en/latest/modules/kaolin.io.shapenet.html#kaolin.io.shapenet.ShapeNetV1), [point_to_mesh_distance](https://kaolin.readthedocs.io/en/latest/modules/kaolin.metrics.trianglemesh.html#kaolin.metrics.trianglemesh.point_to_mesh_distance) and [sided_distance](https://kaolin.readthedocs.io/en/latest/modules/kaolin.metrics.pointcloud.html#kaolin.metrics.pointcloud.sided_distance).\n* [Text2Mesh](https://github.com/threedle/text2mesh):\n    * Use [Kaolin's rendering functions](https://kaolin.readthedocs.io/en/latest/modules/kaolin.render.mesh.html#), [camera functions](https://kaolin.readthedocs.io/en/latest/modules/kaolin.render.camera.html), and [obj](https://kaolin.readthedocs.io/en/latest/modules/kaolin.io.obj.html#kaolin.io.obj.import_mesh) and [off](https://kaolin.readthedocs.io/en/latest/modules/kaolin.io.off.html#kaolin.io.off.import_mesh) importers.\n* [Flexible Isosurface Extraction for Gradient-Based Mesh Optimization (FlexiCubes)\n](https://github.com/nv-tlabs/FlexiCubes):\n    * Use [Flexicube class](https://kaolin.readthedocs.io/en/latest/modules/kaolin.non_commercial.html#kaolin.non_commercial.FlexiCubes), [obj loader](https://kaolin.readthedocs.io/en/latest/modules/kaolin.io.obj.html), [turntable visualizer](https://kaolin.readthedocs.io/en/latest/modules/kaolin.visualize.html#kaolin.visualize.IpyTurntableVisualizer)\n* [SATR](https://github.com/Samir55/SATR):\n    * Use [Kaolin's rendering functions](https://kaolin.readthedocs.io/en/latest/modules/kaolin.render.mesh.html#), [lighting functions](https://kaolin.readthedocs.io/en/latest/modules/kaolin.render.lighting.html),  [camera functions](https://kaolin.readthedocs.io/en/latest/modules/kaolin.render.camera.html), and [obj](https://kaolin.readthedocs.io/en/latest/modules/kaolin.io.obj.html#kaolin.io.obj.import_mesh)/[off](https://kaolin.readthedocs.io/en/latest/modules/kaolin.io.off.html#kaolin.io.off.import_mesh) importers.\n\n## Licenses\n\nMost of Kaolin's repository is under [Apache v2.0 license](LICENSE), except under [kaolin/non_commercial](kaolin/non_commercial/) which is under [NSCL license](LICENSE.NSCL) restricted to non commercial usage for research and evaluation purposes. For example, FlexiCubes method is included under [non_commercial](kaolin/non_commercial/flexicubes/flexicubes.py).\n\nDefault `kaolin` import includes Apache-licensed components:\n```\nimport kaolin\n```\n\nThe non-commercial components need to be explicitly imported as:\n```\nimport kaolin.non_commercial\n```\n\n## Citation\n\nIf you are using Kaolin library for your research, please cite:\n\n```\n@software{KaolinLibrary,\n      author = {Fuji Tsang, Clement and Shugrina, Maria and Lafleche, Jean Francois and Perel, Or and Loop, Charles and Takikawa, Towaki and Modi, Vismay and Zook, Alexander and Wang, Jiehan and Chen, Wenzheng and Shen, Tianchang and Gao, Jun and Jatavallabhula, Krishna Murthy and Smith, Edward and Rozantsev, Artem and Fidler, Sanja and State, Gavriel and Gorski, Jason and Xiang, Tommy and Li, Jianing and Li, Michael and Lebaredian, Rev},\n      title = {Kaolin: A Pytorch Library for Accelerating 3D Deep Learning Research},\n      date = {2024-11-20},\n      version = {0.17.0},\n      url={\\url{https://github.com/NVIDIAGameWorks/kaolin}}\n}\n```\n\n## Contributors\n\nCurrent Team:\n\n- Technical Lead: Clement Fuji Tsang\n- Manager: Maria (Masha) Shugrina\n- Charles Loop\n- Vismay Modi\n- Or Perel\n- Alexander Zook\n\nOther Majors Contributors:\n\n- Wenzheng Chen\n- Sanja Fidler\n- Jun Gao\n- Jason Gorski\n- Jean-Francois Lafleche\n- Rev Lebaredian\n- Jianing Li\n- Michael Li\n- Krishna Murthy Jatavallabhula\n- Artem Rozantsev\n- Tianchang (Frank) Shen\n- Edward Smith\n- Gavriel State\n- Towaki Takikawa\n- Jiehan Wang\n- Tommy Xiang\n","funding_links":[],"categories":["Python","Sensor Processing","Pytorch \u0026 related libraries｜Pytorch \u0026 相关库","Deep Learning Framework","Pytorch \u0026 related libraries"],"sub_categories":["Lidar and Point Cloud Processing","Other libraries｜其他库:","High-Level DL APIs","Other libraries:"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNVIDIAGameWorks%2Fkaolin","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FNVIDIAGameWorks%2Fkaolin","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNVIDIAGameWorks%2Fkaolin/lists"}