{"id":26718818,"url":"https://github.com/ekut-es/lidaraug","last_synced_at":"2025-04-14T03:51:21.417Z","repository":{"id":262808702,"uuid":"709779749","full_name":"ekut-es/LidarAug","owner":"ekut-es","description":"Augmentation Library for LiDAR Point Clouds","archived":false,"fork":false,"pushed_at":"2025-01-16T13:53:27.000Z","size":4622,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-27T17:51:41.644Z","etag":null,"topics":["augmentation","lidar","lidar-point-cloud","self-driving"],"latest_commit_sha":null,"homepage":"https://lidaraug.readthedocs.io/en/latest/","language":"C++","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/ekut-es.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"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":"2023-10-25T11:39:26.000Z","updated_at":"2025-01-29T11:06:40.000Z","dependencies_parsed_at":"2024-12-12T08:22:49.289Z","dependency_job_id":"a5adbe80-d2d8-447d-9706-4bf7cf8757f4","html_url":"https://github.com/ekut-es/LidarAug","commit_stats":null,"previous_names":["ekut-es/lidaraug"],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ekut-es%2FLidarAug","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ekut-es%2FLidarAug/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ekut-es%2FLidarAug/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ekut-es%2FLidarAug/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ekut-es","download_url":"https://codeload.github.com/ekut-es/LidarAug/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248819351,"owners_count":21166473,"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":["augmentation","lidar","lidar-point-cloud","self-driving"],"created_at":"2025-03-27T17:50:20.468Z","updated_at":"2025-04-14T03:51:21.398Z","avatar_url":"https://github.com/ekut-es.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LidarAug\n\nA toolbox for LiDAR point cloud data, providing point cloud transformations, point cloud augmentation, realistic weather simulation and 2D \u0026 3D AP evaluation, with an easy-to-use Python API.\nThis module supports several essential tasks for the development of LiDAR-based perception methods in automated driving.\n\n## Installation\n\nFirst clone and enter the repository:\n\n`git clone https://github.com/ekut-es/LidarAug \u0026\u0026 cd LidarAug`\n\n### C++ library\n\nThe following dependencies are necessary to build and test the C++ library for development:\n\n- [libtorch](https://pytorch.org/get-started/locally/)\n- [google test](https://github.com/google/googletest)\n- [boost](https://www.boost.org/)\n- [OpenMP](https://www.openmp.org/resources/openmp-compilers-tools/)\n\nIt is also necessary to set the environment variable `TORCH_PATH` to point to where `libtorch` is installed on your\nsystem.\n\nAfter that, just run `make ctest` to compile the library and run google test.\n\n*Note that the tests written for the backend include some controlled RNG tests which might fail on different platforms with different architectures such as the Apple MX chips. The tests were developed for Linux x86 using GCC.*\n\n### Python module\n\nThe following dependencies are necessary to install the Python module:\n\n- [PyTorch/libtorch](https://pytorch.org/get-started/locally/)\n- [boost](https://www.boost.org/)\n- [OpenMP](https://www.openmp.org/resources/openmp-compilers-tools/)\n- [cnpy](https://github.com/TomSchammo/cnpy)\n- [pybind11](https://github.com/pybind/pybind11)\n\nTo use the Python module, just run `make install` after cloning and entering the repository.\n\nTo test the python functions/wrappers, install [pytest](https://docs.pytest.org/en/8.0.x/) (`pip install pytest`) and\nrun `make testpy`.\n\nThe required Python version is 3.11.\n\n#### Submodules\n\nThe `lidar_aug` Python module contains 5 submodules:\n\n1. **transformations:**\n\n`transformations` contains any C++ enums, structs and functions that have bindings and are used for transformations.\n\n2. **weather_simulations:**\n\n`weather_simulations` contains any C++ enums, structs and functions that have bindings and are used for weather\nsimulations.\n\n3. **augmentations:**\n\n`augmentations` contains the Python wrappers for any C++ function (weather simulation or transformation).\n\n4. **evaluation:**\n\n`evaluation` contains (C++) function to evaluate the accuracy of bounding boxes.\nThis can be done for 2D and 3D bounding boxes.\n\n5. **point_cloud:**\n\n`point_cloud` contains things that is specific to point clouds that is used across modules and functionally not\nspecific to the task of one of those.\nSuch as the `IntensityRange` enum that is used to set/determine the maximum intensity of the points in a point cloud.\n\n\n### Docker\n\nAlternatively the module can be run inside a [Docker](https://www.docker.com/) container.\n\nAfter installing [Docker](https://www.docker.com/) and cloning the repository, all you need to do is run `make docker`,\nwhich will start building the image and automatically run the tests during the build process.\n\nNOTE: If you're running the docker image on ARM run `make docker-arm` instead.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fekut-es%2Flidaraug","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fekut-es%2Flidaraug","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fekut-es%2Flidaraug/lists"}