{"id":13444163,"url":"https://github.com/Yang7879/3D-BoNet","last_synced_at":"2025-03-20T18:31:25.508Z","repository":{"id":108729501,"uuid":"189902521","full_name":"Yang7879/3D-BoNet","owner":"Yang7879","description":"🔥3D-BoNet in Tensorflow (NeurIPS 2019, Spotlight)","archived":false,"fork":false,"pushed_at":"2021-03-02T12:54:20.000Z","size":73466,"stargazers_count":393,"open_issues_count":54,"forks_count":85,"subscribers_count":11,"default_branch":"master","last_synced_at":"2024-10-28T08:39:33.149Z","etag":null,"topics":["3d-object-detection","3d-point-clouds","3d-vision","computer-vision","instance-segmentation"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1906.01140","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Yang7879.png","metadata":{"files":{"readme":"README.md","changelog":null,"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}},"created_at":"2019-06-02T22:44:03.000Z","updated_at":"2024-10-12T05:46:36.000Z","dependencies_parsed_at":"2023-03-06T03:00:18.827Z","dependency_job_id":null,"html_url":"https://github.com/Yang7879/3D-BoNet","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/Yang7879%2F3D-BoNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Yang7879%2F3D-BoNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Yang7879%2F3D-BoNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Yang7879%2F3D-BoNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Yang7879","download_url":"https://codeload.github.com/Yang7879/3D-BoNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244670137,"owners_count":20490925,"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","3d-point-clouds","3d-vision","computer-vision","instance-segmentation"],"created_at":"2024-07-31T03:02:20.677Z","updated_at":"2025-03-20T18:31:21.797Z","avatar_url":"https://github.com/Yang7879.png","language":"Python","funding_links":[],"categories":["Python","Appendix: Object Detection for Natural Scene"],"sub_categories":["Papers"],"readme":"## Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds\nBo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni. [arXiv:1906.01140](https://arxiv.org/abs/1906.01140), 2019.\n### (1) Setup\nubuntu 16.04 + cuda 8.0\n\npython 2.7 or 3.6\n\ntensorflow 1.2 or 1.4\n\nscipy 1.3\n\nh5py 2.9\n\nopen3d-python 0.3.0\n\n#### Compile tf_ops\n(1) To find tensorflow include path and library paths:\n\n    import tensorflow as tf\n    print(tf.sysconfig.get_include())\n    print(tf.sysconfig.get_lib())\n\n(2) To change the path in all the complie files, e.g. tf_ops/sampling/tf_sampling_compile.sh, and then compile:\n\n    cd tf_ops/sampling\n    chmod +x tf_sampling_compile.sh\n    ./tf_sampling_compile.sh\n\n### (2) Data\nS3DIS: [https://drive.google.com/open?id=1hOsoOqOWKSZIgAZLu2JmOb_U8zdR04v0](https://drive.google.com/open?id=1hOsoOqOWKSZIgAZLu2JmOb_U8zdR04v0)\n\n百度盘: [https://pan.baidu.com/s/1ww_Fs2D9h7_bA2HfNIa2ig](https://pan.baidu.com/s/1ww_Fs2D9h7_bA2HfNIa2ig) 密码:qpt7\n\nAcknowledgement: we use the same data released by [JSIS3D](https://github.com/pqhieu/jsis3d).\n\n### (3) Train/test\npython main_train.py\n\npython main_eval.py\n\n### (4) Quantitative Results on ScanNet\n![Arch Image](https://github.com/Yang7879/3D-BoNet/blob/master/figs/fig_res_scannet.png)\n### (5) Qualitative Results on ScanNet\n![Arch Image](https://github.com/Yang7879/3D-BoNet/blob/master/figs/fig_ins_scannet.png)\n\n| ![2](./figs/fig_scannet_scene0015.gif)   | ![z](./figs/fig_scannet_scene0081.gif) |\n| ---------------------------------------- | -------------------------------------- |\n| ![z](./figs/fig_scannet_scene0088.gif)   | ![z](./figs/fig_scannet_scene0196.gif) |\n\n#### More results of ScanNet validation split are available at: [More ScanNet Results](https://drive.google.com/file/d/1cV07rP02Yi3Eu6GQxMR2buigNPJEvCq0/view?usp=sharing)\nTo visualize:\npython helper_data_scannet.py\n\n### (6) Qualitative Results on S3DIS\n| ![z](./figs/fig_s3dis_area2_auditorium.gif)   | ![z](./figs/fig_s3dis_area6_hallway1.gif) |\n| --------------------------------------------- | ----------------------------------------- |\n\n![Teaser Image](https://github.com/Yang7879/3D-BoNet/blob/master/figs/fig_bb_s3dis.png)\n### (7) Training Curves on S3DIS\n![Teaser Image](https://github.com/Yang7879/3D-BoNet/blob/master/figs/fig_traincurv_s3dis.png)\n\n### (8) Video Demo (Youtube)\n\u003cp align=\"center\"\u003e \u003ca href=\"https://www.youtube.com/watch?v=Bk727Ec10Ao\"\u003e\u003cimg src=\"./figs/fig_video_demo_cover.png\" width=\"80%\"\u003e\u003c/a\u003e \u003c/p\u003e\n\n### Citation\nIf you find our work useful in your research, please consider citing:\n\n    @inproceedings{yang2019learning,\n      title={Learning object bounding boxes for 3d instance segmentation on point clouds},\n      author={Yang, Bo and Wang, Jianan and Clark, Ronald and Hu, Qingyong and Wang, Sen and Markham, Andrew and Trigoni, Niki},\n      booktitle={Advances in Neural Information Processing Systems},\n      pages={6737--6746},\n      year={2019}\n    }\n    \n## Related Repos\n1. [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://github.com/QingyongHu/RandLA-Net) ![GitHub stars](https://img.shields.io/github/stars/QingyongHu/RandLA-Net.svg?style=flat\u0026label=Star)\n2. [SoTA-Point-Cloud: Deep Learning for 3D Point Clouds: A Survey](https://github.com/QingyongHu/SoTA-Point-Cloud) ![GitHub stars](https://img.shields.io/github/stars/QingyongHu/SoTA-Point-Cloud.svg?style=flat\u0026label=Star)\n3. [SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds](https://github.com/QingyongHu/SpinNet) ![GitHub stars](https://img.shields.io/github/stars/QingyongHu/SensatUrban.svg?style=flat\u0026label=Star)\n4. [SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration](https://github.com/QingyongHu/SpinNet) ![GitHub stars](https://img.shields.io/github/stars/QingyongHu/SpinNet.svg?style=flat\u0026label=Star)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYang7879%2F3D-BoNet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FYang7879%2F3D-BoNet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYang7879%2F3D-BoNet/lists"}