{"id":22482467,"url":"https://github.com/hzxie/grnet","last_synced_at":"2025-04-06T10:11:02.605Z","repository":{"id":38363287,"uuid":"200205888","full_name":"hzxie/GRNet","owner":"hzxie","description":"The official implementation of \"GRNet: Gridding Residual Network for Dense Point Cloud Completion\".  (ECCV 2020)","archived":false,"fork":false,"pushed_at":"2024-01-23T08:12:15.000Z","size":1251,"stargazers_count":321,"open_issues_count":2,"forks_count":57,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-30T09:06:52.049Z","etag":null,"topics":["3d-object-reconstruction","aten","cubic-feature-sampling","eccv-2020","gridding","point-cloud-completion","pytorch"],"latest_commit_sha":null,"homepage":"https://haozhexie.com/project/grnet","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/hzxie.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-08-02T09:21:53.000Z","updated_at":"2025-03-26T08:38:18.000Z","dependencies_parsed_at":"2022-08-27T01:00:41.008Z","dependency_job_id":"117708f9-f14a-445b-95ea-2e4eba6f3cc4","html_url":"https://github.com/hzxie/GRNet","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/hzxie%2FGRNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hzxie%2FGRNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hzxie%2FGRNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hzxie%2FGRNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hzxie","download_url":"https://codeload.github.com/hzxie/GRNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247464220,"owners_count":20942970,"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-reconstruction","aten","cubic-feature-sampling","eccv-2020","gridding","point-cloud-completion","pytorch"],"created_at":"2024-12-06T16:26:06.409Z","updated_at":"2025-04-06T10:11:02.567Z","avatar_url":"https://github.com/hzxie.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# GRNet\n\nThis repository contains the source code for the paper [GRNet: Gridding Residual Network for Dense Point Cloud Completion](https://arxiv.org/abs/2006.03761).\n\n[![codebeat badge](https://codebeat.co/badges/4e490a68-1a17-4274-a9f8-d7521458eb7f)](https://codebeat.co/projects/github-com-hzxie-grnet-master)\n\n![Overview](https://www.infinitescript.com/projects/GRNet/GRNet-Overview.png)\n\n## Cite this work\n\n```\n@inproceedings{xie2020grnet,\n  title={GRNet: Gridding Residual Network for Dense Point Cloud Completion},\n  author={Xie, Haozhe and \n          Yao, Hongxun and \n          Zhou, Shangchen and \n          Mao, Jiageng and \n          Zhang, Shengping and \n          Sun, Wenxiu},\n  booktitle={ECCV},\n  year={2020}\n}\n```\n\n## Datasets\n\nWe use the [ShapeNet](https://www.shapenet.org/), [Compeletion3D](http://completion3d.stanford.edu/), and [KITTI](http://www.cvlibs.net/datasets/kitti/) datasets in our experiments, which are available below:\n\n- [ShapeNet](https://drive.google.com/drive/folders/1P_W1tz5Q4ZLapUifuOE4rFAZp6L1XTJz)\n- [Completion3D](http://download.cs.stanford.edu/downloads/completion3d/dataset2019.zip)\n- [KITTI](https://drive.google.com/drive/folders/1fSu0_huWhticAlzLh3Ejpg8zxzqO1z-F)\n\n## Pretrained Models\n\nThe pretrained models on ShapeNet are available as follows:\n\n- [GRNet for ShapeNet](https://gateway.infinitescript.com/?fileName=GRNet-ShapeNet.pth) (306.8 MB)\n- [GRNet for KITTI](https://gateway.infinitescript.com/?fileName=GRNet-KITTI.pth) (306.8 MB)\n\n## Prerequisites\n\n#### Clone the Code Repository\n\n```\ngit clone https://github.com/hzxie/GRNet.git\n```\n\n#### Install Python Denpendencies\n\n```\ncd GRNet\npip install -r requirements.txt\n```\n\n#### Build PyTorch Extensions\n\n**NOTE:** PyTorch \u003e= 1.4, CUDA \u003e= 9.0 and GCC \u003e= 4.9 are required.\n\n```\nGRNET_HOME=`pwd`\n\n# Chamfer Distance\ncd $GRNET_HOME/extensions/chamfer_dist\npython setup.py install --user\n\n# Cubic Feature Sampling\ncd $GRNET_HOME/extensions/cubic_feature_sampling\npython setup.py install --user\n\n# Gridding \u0026 Gridding Reverse\ncd $GRNET_HOME/extensions/gridding\npython setup.py install --user\n\n# Gridding Loss\ncd $GRNET_HOME/extensions/gridding_loss\npython setup.py install --user\n```\n\n#### Preprocess the ShapeNet dataset\n\n```\ncd $GRNET_HOME/utils\npython lmdb_serializer.py /path/to/shapenet/train.lmdb /path/to/output/shapenet/train\npython lmdb_serializer.py /path/to/shapenet/valid.lmdb /path/to/output/shapenet/val\n```\n\nYou can download the processed ShapeNet dataset [here](https://gateway.infinitescript.com/?fileName=ShapeNetCompletion).\n\n#### Update Settings in `config.py`\n\nYou need to update the file path of the datasets:\n\n```\n__C.DATASETS.COMPLETION3D.PARTIAL_POINTS_PATH    = '/path/to/datasets/Completion3D/%s/partial/%s/%s.h5'\n__C.DATASETS.COMPLETION3D.COMPLETE_POINTS_PATH   = '/path/to/datasets/Completion3D/%s/gt/%s/%s.h5'\n__C.DATASETS.SHAPENET.PARTIAL_POINTS_PATH        = '/path/to/datasets/ShapeNet/ShapeNetCompletion/%s/partial/%s/%s/%02d.pcd'\n__C.DATASETS.SHAPENET.COMPLETE_POINTS_PATH       = '/path/to/datasets/ShapeNet/ShapeNetCompletion/%s/complete/%s/%s.pcd'\n__C.DATASETS.KITTI.PARTIAL_POINTS_PATH           = '/path/to/datasets/KITTI/cars/%s.pcd'\n__C.DATASETS.KITTI.BOUNDING_BOX_FILE_PATH        = '/path/to/datasets/KITTI/bboxes/%s.txt'\n\n# Dataset Options: Completion3D, ShapeNet, ShapeNetCars, KITTI\n__C.DATASET.TRAIN_DATASET                        = 'ShapeNet'\n__C.DATASET.TEST_DATASET                         = 'ShapeNet'\n```\n\n## Get Started\n\nTo train GRNet, you can simply use the following command:\n\n```\npython3 runner.py\n```\n\nTo test GRNet, you can use the following command:\n\n```\npython3 runner.py --test --weights=/path/to/pretrained/model.pth\n```\n\n## License\n\nThis project is open sourced under MIT license.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhzxie%2Fgrnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhzxie%2Fgrnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhzxie%2Fgrnet/lists"}