{"id":13443522,"url":"https://github.com/xinge008/Cylinder3D","last_synced_at":"2025-03-20T16:31:44.215Z","repository":{"id":37980181,"uuid":"284422543","full_name":"xinge008/Cylinder3D","owner":"xinge008","description":"Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)","archived":false,"fork":false,"pushed_at":"2023-04-05T08:18:32.000Z","size":669,"stargazers_count":835,"open_issues_count":55,"forks_count":179,"subscribers_count":15,"default_branch":"master","last_synced_at":"2024-08-01T03:43:53.571Z","etag":null,"topics":["cvpr2021","lidar-point-cloud","lidar-segmentation","nuscenes","panoptic-segmentation","point-cloud","semantic-segmentation","semantickitti"],"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/xinge008.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":"2020-08-02T08:33:00.000Z","updated_at":"2024-07-30T16:06:34.000Z","dependencies_parsed_at":"2023-01-28T06:46:04.122Z","dependency_job_id":"ae1a176f-d038-4be6-9663-e7b2a15f862d","html_url":"https://github.com/xinge008/Cylinder3D","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/xinge008%2FCylinder3D","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinge008%2FCylinder3D/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinge008%2FCylinder3D/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinge008%2FCylinder3D/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xinge008","download_url":"https://codeload.github.com/xinge008/Cylinder3D/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221780034,"owners_count":16879040,"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":["cvpr2021","lidar-point-cloud","lidar-segmentation","nuscenes","panoptic-segmentation","point-cloud","semantic-segmentation","semantickitti"],"created_at":"2024-07-31T03:02:02.832Z","updated_at":"2024-10-28T04:31:14.283Z","avatar_url":"https://github.com/xinge008.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"\n# Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation\n\n The source code of our work **\"Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation**\n![img|center](./img/pipeline.png)\n\n## News\n- **2022-06 [NEW:fire:]** **PVKD (CVPR2022)**, a lightweight Cylinder3D model with much higher performance has been released [here](https://github.com/cardwing/Codes-for-PVKD)\n-  Cylinder3D is accepted to CVPR 2021 as an **Oral** presentation\n-  Cylinder3D achieves the **1st place** in the leaderboard of SemanticKITTI **multiscan** semantic segmentation\n\u003cp align=\"center\"\u003e\n   \u003cimg src=\"./img/leaderboard2.png\" width=\"30%\"\u003e \n\u003c/p\u003e\n\n- Cylinder3D achieves the 2nd place in the challenge of nuScenes LiDAR segmentation, with mIoU=0.779, fwIoU=0.899 and FPS=10Hz.\n- **2020-12** We release the new version of Cylinder3D with nuScenes dataset support.\n- **2020-11** We preliminarily release the Cylinder3D--v0.1, supporting the LiDAR semantic segmentation on SemanticKITTI and nuScenes.\n- **2020-11** Our work achieves the **1st place** in the leaderboard of SemanticKITTI semantic segmentation (until CVPR2021 DDL, still rank 1st in term of Accuracy now), and based on the proposed method, we also achieve the **1st place** in the leaderboard of SemanticKITTI panoptic segmentation.\n\n\u003cp align=\"center\"\u003e\n   \u003cimg src=\"./img/leaderboard.png\" width=\"40%\"\u003e \n\u003c/p\u003e\n\n## Installation\n\n### Requirements\n- PyTorch \u003e= 1.2 \n- yaml\n- Cython\n- [torch-scatter](https://github.com/rusty1s/pytorch_scatter)\n- [nuScenes-devkit](https://github.com/nutonomy/nuscenes-devkit) (optional for nuScenes)\n- [spconv](https://github.com/traveller59/spconv) (tested with spconv==1.2.1 and cuda==10.2)\n\n## Data Preparation\n\n### SemanticKITTI\n```\n./\n├── \n├── ...\n└── path_to_data_shown_in_config/\n    ├──sequences\n        ├── 00/           \n        │   ├── velodyne/\t\n        |   |\t├── 000000.bin\n        |   |\t├── 000001.bin\n        |   |\t└── ...\n        │   └── labels/ \n        |       ├── 000000.label\n        |       ├── 000001.label\n        |       └── ...\n        ├── 08/ # for validation\n        ├── 11/ # 11-21 for testing\n        └── 21/\n\t    └── ...\n```\n\n### nuScenes\n```\n./\n├── \n├── ...\n└── path_to_data_shown_in_config/\n\t\t├──v1.0-trainval\n\t\t├──v1.0-test\n\t\t├──samples\n\t\t├──sweeps\n\t\t├──maps\n\n```\n\n## Training\n1. modify the config/semantickitti.yaml with your custom settings. We provide a sample yaml for SemanticKITTI\n2. train the network by running \"sh train.sh\"\n\n### Training for nuScenes\nPlease refer to [NUSCENES-GUIDE](./NUSCENES-GUIDE.md)\n\n### Pretrained Models\n-- We provide a pretrained model for SemanticKITTI [LINK1](https://drive.google.com/file/d/1q4u3LlQXz89LqYW3orXL5oTs_4R2eS8P/view?usp=sharing) or [LINK2](https://pan.baidu.com/s/1c0oIL2QTTcjCo9ZEtvOIvA) (access code: xqmi)\n\n-- For nuScenes dataset, please refer to [NUSCENES-GUIDE](./NUSCENES-GUIDE.md)\n\n## Semantic segmentation demo for a folder of lidar scans\n```\npython demo_folder.py --demo-folder YOUR_FOLDER --save-folder YOUR_SAVE_FOLDER\n```\nIf you want to validate with your own datasets, you need to provide labels.\n--demo-label-folder is optional\n```\npython demo_folder.py --demo-folder YOUR_FOLDER --save-folder YOUR_SAVE_FOLDER --demo-label-folder YOUR_LABEL_FOLDER\n```\n\n## TODO List\n- [x] Release pretrained model for nuScenes.\n- [x] Support multiscan semantic segmentation.\n- [ ] Support more models, including PolarNet, RandLA, SequeezeV3 and etc.\n- [ ] Integrate LiDAR Panotic Segmentation into the codebase.\n\n## Reference\n\nIf you find our work useful in your research, please consider citing our [paper](https://arxiv.org/pdf/2011.10033):\n```\n@article{zhu2020cylindrical,\n  title={Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation},\n  author={Zhu, Xinge and Zhou, Hui and Wang, Tai and Hong, Fangzhou and Ma, Yuexin and Li, Wei and Li, Hongsheng and Lin, Dahua},\n  journal={arXiv preprint arXiv:2011.10033},\n  year={2020}\n}\n\n#for LiDAR panoptic segmentation\n@article{hong2020lidar,\n  title={LiDAR-based Panoptic Segmentation via Dynamic Shifting Network},\n  author={Hong, Fangzhou and Zhou, Hui and Zhu, Xinge and Li, Hongsheng and Liu, Ziwei},\n  journal={arXiv preprint arXiv:2011.11964},\n  year={2020}\n}\n```\n\n## Acknowledgments\nWe thanks for the opensource codebases, [PolarSeg](https://github.com/edwardzhou130/PolarSeg) and [spconv](https://github.com/traveller59/spconv)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxinge008%2FCylinder3D","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxinge008%2FCylinder3D","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxinge008%2FCylinder3D/lists"}