Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)
Alternatives To Cylinder3d
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
Labelme10,4618821 hours ago177March 03, 202271otherPython
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
Segmentation_models.pytorch7,353234a day ago10November 18, 202126mitPython
Segmentation models with pretrained backbones. PyTorch.
Paddleseg7,152212 hours ago8April 20, 2022273apache-2.0Python
Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.
Pytorch Unet6,465
3 months ago49gpl-3.0Python
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
Mmsegmentation5,870214 hours ago30July 01, 2022417apache-2.0Jupyter Notebook
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
Gluon Cv5,42215444 months ago1,514July 07, 202261apache-2.0Python
Gluon CV Toolkit
Hrnet Semantic Segmentation2,714
7 months ago151otherPython
The OCR approach is rephrased as Segmentation Transformer: This is an official implementation of semantic segmentation for HRNet.
Imgclsmob2,3994a year ago67September 21, 20216mitPython
Sandbox for training deep learning networks
Awesome Semantic Segmentation Pytorch2,399
5 months ago114apache-2.0Python
Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)
Semantic Segmentation Suite2,311
2 years ago83Python
Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!
Alternatives To Cylinder3d
Select To Compare

Alternative Project Comparisons

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

The source code of our work "Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation img|center


  • 2022-06 [NEW🔥] PVKD (CVPR2022), a lightweight Cylinder3D model with much higher performance has been released here
  • Cylinder3D is accepted to CVPR 2021 as an Oral presentation
  • Cylinder3D achieves the 1st place in the leaderboard of SemanticKITTI multiscan semantic segmentation

  • Cylinder3D achieves the 2nd place in the challenge of nuScenes LiDAR segmentation, with mIoU=0.779, fwIoU=0.899 and FPS=10Hz.
  • 2020-12 We release the new version of Cylinder3D with nuScenes dataset support.
  • 2020-11 We preliminarily release the Cylinder3D--v0.1, supporting the LiDAR semantic segmentation on SemanticKITTI and nuScenes.
  • 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.



Data Preparation


├── ...
└── path_to_data_shown_in_config/
        ├── 00/           
        │   ├── velodyne/	
        |   |	├── 000000.bin
        |   |	├── 000001.bin
        |   |	└── ...
        │   └── labels/ 
        |       ├── 000000.label
        |       ├── 000001.label
        |       └── ...
        ├── 08/ # for validation
        ├── 11/ # 11-21 for testing
        └── 21/
	    └── ...


├── ...
└── path_to_data_shown_in_config/


  1. modify the config/semantickitti.yaml with your custom settings. We provide a sample yaml for SemanticKITTI
  2. train the network by running "sh"

Training for nuScenes

Please refer to NUSCENES-GUIDE

Pretrained Models

-- We provide a pretrained model for SemanticKITTI LINK1 or LINK2 (access code: xqmi)

-- For nuScenes dataset, please refer to NUSCENES-GUIDE

Semantic segmentation demo for a folder of lidar scans

python --demo-folder YOUR_FOLDER --save-folder YOUR_SAVE_FOLDER

If you want to validate with your own datasets, you need to provide labels. --demo-label-folder is optional

python --demo-folder YOUR_FOLDER --save-folder YOUR_SAVE_FOLDER --demo-label-folder YOUR_LABEL_FOLDER


  • [x] Release pretrained model for nuScenes.
  • [x] Support multiscan semantic segmentation.
  • [ ] Support more models, including PolarNet, RandLA, SequeezeV3 and etc.
  • [ ] Integrate LiDAR Panotic Segmentation into the codebase.


If you find our work useful in your research, please consider citing our paper:

  title={Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation},
  author={Zhu, Xinge and Zhou, Hui and Wang, Tai and Hong, Fangzhou and Ma, Yuexin and Li, Wei and Li, Hongsheng and Lin, Dahua},
  journal={arXiv preprint arXiv:2011.10033},

#for LiDAR panoptic segmentation
  title={LiDAR-based Panoptic Segmentation via Dynamic Shifting Network},
  author={Hong, Fangzhou and Zhou, Hui and Zhu, Xinge and Li, Hongsheng and Liu, Ziwei},
  journal={arXiv preprint arXiv:2011.11964},


We thanks for the opensource codebases, PolarSeg and spconv

Popular Segmentation Projects
Popular Semantic Segmentation Projects
Popular Machine Learning Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Point Cloud
Semantic Segmentation