{"id":14286903,"url":"https://github.com/sky77764/pa-aug.pytorch","last_synced_at":"2025-08-15T07:31:34.703Z","repository":{"id":45793858,"uuid":"291918864","full_name":"sky77764/pa-aug.pytorch","owner":"sky77764","description":"Part-Aware Data Augmentation for 3D Object Detection in Point Cloud (IROS 2021)","archived":false,"fork":false,"pushed_at":"2022-10-23T05:38:25.000Z","size":335,"stargazers_count":78,"open_issues_count":1,"forks_count":17,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-08-24T17:26:26.219Z","etag":null,"topics":["3d-object-detection","data-augmentation","lidar","point-cloud"],"latest_commit_sha":null,"homepage":"","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/sky77764.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}},"created_at":"2020-09-01T06:45:35.000Z","updated_at":"2024-07-30T16:41:09.000Z","dependencies_parsed_at":"2023-01-20T16:47:29.225Z","dependency_job_id":null,"html_url":"https://github.com/sky77764/pa-aug.pytorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sky77764%2Fpa-aug.pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sky77764%2Fpa-aug.pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sky77764%2Fpa-aug.pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sky77764%2Fpa-aug.pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sky77764","download_url":"https://codeload.github.com/sky77764/pa-aug.pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":229899538,"owners_count":18141525,"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-object-detection","data-augmentation","lidar","point-cloud"],"created_at":"2024-08-23T17:01:06.576Z","updated_at":"2024-12-16T02:30:26.800Z","avatar_url":"https://github.com/sky77764.png","language":"Python","funding_links":[],"categories":["Beyond Vision"],"sub_categories":["**3D Point**"],"readme":"# Part-Aware Data Augmentation for 3D Object Detection in Point Cloud\n\nThis repository contains a reference implementation of our [Part-Aware Data Augmentation for 3D Object Detection in Point Cloud](https://ieeexplore.ieee.org/document/9635887) (IROS 2021).\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/methods.jpg\" width=\"100%\" height=\"400\"\u003e\n\u003c/p\u003e\n\n\nIf you find this code useful in your research, please consider citing our work:\n```\n@inproceedings{choi2021part,\n  title={Part-aware data augmentation for 3d object detection in point cloud},\n  author={Choi, Jaeseok and Song, Yeji and Kwak, Nojun},\n  booktitle={2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},\n  pages={3391--3397},\n  year={2021},\n  organization={IEEE}\n}\n```\n## Prerequisites\nOur code was tested on [second.pytorch](https://github.com/traveller59/second.pytorch) and [OpenPCDet](https://github.com/open-mmlab/OpenPCDet).  \nThis repository contains only part-aware data augmentation code.  \nRefer to the link above for code such as data loader or detector.\n\n## Usage\n```\nArgs:\n    ** only supports KITTI format **\n    points: lidar points (N, 4), \n    gt_boxes: ground truth boxes (B, 7),\n    gt_names: ground truth classes (B, 1), \n    class_names: list of classes to augment (3),\n    pa_aug_param: parameters for PA_AUG (string).\n\nReturns:\n    points: augmented lidar points (N', 4),\n    gt_boxes_mask: mask for gt_boxes (B)\n\n\nclass_names = ['Car', 'Pedestrian', 'Cyclist']\npa_aug_param = \"dropout_p02_swap_p02_mix_p02_sparse40_p01_noise10_p01\"\n\npa_aug = PartAwareAugmentation(points, gt_boxes, gt_names, class_names=class_names)\npoints, gt_boxes_mask = pa_aug.augment(pa_aug_param=pa_aug_param)\ngt_boxes = gt_boxes[gt_boxes_mask]\n```\n\n## Example\nFollow [this repo](https://github.com/sky77764/PA-AUG-MD3D) if you want to check the implementation on OpenPCDet.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsky77764%2Fpa-aug.pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsky77764%2Fpa-aug.pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsky77764%2Fpa-aug.pytorch/lists"}