{"id":13443898,"url":"https://github.com/Yochengliu/DensePoint","last_synced_at":"2025-03-20T17:32:18.217Z","repository":{"id":117936946,"uuid":"199966519","full_name":"Yochengliu/DensePoint","owner":"Yochengliu","description":"DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing (ICCV 2019)","archived":false,"fork":false,"pushed_at":"2021-09-30T11:43:20.000Z","size":1967,"stargazers_count":119,"open_issues_count":9,"forks_count":24,"subscribers_count":10,"default_branch":"master","last_synced_at":"2025-03-13T21:07:15.866Z","etag":null,"topics":["3d-convolutional-network","3d-graphics","3d-point-clouds","3d-shape-recognition","3d-shape-segmentation","artificial-intelligence","convolutional-neural-networks","deep-learning","geometric-deep-learning","normal-estimation"],"latest_commit_sha":null,"homepage":"","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/Yochengliu.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":"2019-08-01T03:05:31.000Z","updated_at":"2025-01-26T19:26:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"4ac6a4da-8ace-4ccd-88b4-348773e46d6c","html_url":"https://github.com/Yochengliu/DensePoint","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/Yochengliu%2FDensePoint","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Yochengliu%2FDensePoint/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Yochengliu%2FDensePoint/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Yochengliu%2FDensePoint/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Yochengliu","download_url":"https://codeload.github.com/Yochengliu/DensePoint/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244660649,"owners_count":20489371,"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-convolutional-network","3d-graphics","3d-point-clouds","3d-shape-recognition","3d-shape-segmentation","artificial-intelligence","convolutional-neural-networks","deep-learning","geometric-deep-learning","normal-estimation"],"created_at":"2024-07-31T03:02:13.306Z","updated_at":"2025-03-20T17:32:13.198Z","avatar_url":"https://github.com/Yochengliu.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"DensePoint\n===\nThis repository contains the code in Pytorch for the paper:\n\n__DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing__ [[arXiv](https://arxiv.org/abs/1909.03669)] [[CVF](http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_DensePoint_Learning_Densely_Contextual_Representation_for_Efficient_Point_Cloud_Processing_ICCV_2019_paper.pdf)]\n\u003cbr\u003e\n[Yongcheng Liu](https://yochengliu.github.io/), [Bin Fan](http://www.nlpr.ia.ac.cn/fanbin/), [Gaofeng Meng](http://www.escience.cn/people/menggaofeng/index.html;jsessionid=EE2E193290F516D1BA8E2E35A09A9A08-n1), [Jiwen Lu](http://ivg.au.tsinghua.edu.cn/Jiwen_Lu/), [Shiming Xiang](https://scholar.google.com/citations?user=0ggsACEAAAAJ\u0026hl=zh-CN) and [Chunhong Pan](http://people.ucas.ac.cn/~0005314)\n\u003cbr\u003e\n[__ICCV 2019__](http://iccv2019.thecvf.com/)\n\n## Citation\n\nIf our paper is helpful for your research, please consider citing:   \n\n        @inproceedings{liu2019densepoint,   \n            author = {Yongcheng Liu and    \n                            Bin Fan and  \n                       Gaofeng Meng and\n                           Jiwen Lu and\n                      Shiming Xiang and   \n                           Chunhong Pan},   \n            title = {DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing},   \n            booktitle = {IEEE International Conference on Computer Vision (ICCV)},    \n            pages = {5239--5248},  \n            year = {2019}   \n        }   \n\n## Usage: Preparation\n\n- Requirement\n\n  - Ubuntu 14.04\n  - Python 3 (recommend Anaconda3)\n  - Pytorch 0.3.\\*\n  - CMake \u003e 2.8\n  - CUDA 8.0 + cuDNN 5.1\n\n- Building Kernel\n\n      git clone https://github.com/Yochengliu/DensePoint.git \n      cd DensePoint\n      mkdir build \u0026\u0026 cd build\n      cmake .. \u0026\u0026 make\n\n- Dataset\n  - Shape Classification: download and unzip [ModelNet40](https://shapenet.cs.stanford.edu/media/modelnet40_ply_hdf5_2048.zip) (415M). Replace `$data_root$` in `cfgs/config_cls.yaml` with the dataset parent path.\n\n## Usage: Training\n- Shape Classification\n\n      sh train_cls.sh\n        \nWe have trained a 6-layer classification model in `cls` folder, whose accuracy is 92.38%.\n\n## Usage: Evaluation\n- Shape Classification\n\n      Voting script: voting_evaluate_cls.py\n        \nYou can use our model `cls/model_cls_L6_iter_36567_acc_0.923825.pth` as the checkpoint in `config_cls.yaml`, and after this voting you will get an accuracy of 92.5% if all things go right.\n\n## License\n\nThe code is released under MIT License (see LICENSE file for details).\n\n## Acknowledgement\n\nThe code is heavily borrowed from [Pointnet2_PyTorch](https://github.com/erikwijmans/Pointnet2_PyTorch).\n        \n## Contact\n\nIf you have some ideas or questions about our research to share with us, please contact \u003cyongcheng.liu@nlpr.ia.ac.cn\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYochengliu%2FDensePoint","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FYochengliu%2FDensePoint","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYochengliu%2FDensePoint/lists"}