{"id":17076857,"url":"https://github.com/wxinlong/asis","last_synced_at":"2025-08-16T16:46:21.044Z","repository":{"id":127985846,"uuid":"172624855","full_name":"WXinlong/ASIS","owner":"WXinlong","description":"Associatively Segmenting Instances and Semantics in Point Clouds, CVPR 2019","archived":false,"fork":false,"pushed_at":"2019-04-27T12:22:24.000Z","size":1715,"stargazers_count":256,"open_issues_count":17,"forks_count":64,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-24T09:48:03.306Z","etag":null,"topics":["deep-learning","instance-segmentation","point-cloud","semantic-segmentation"],"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/WXinlong.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":"2019-02-26T02:46:20.000Z","updated_at":"2025-01-14T07:14:23.000Z","dependencies_parsed_at":null,"dependency_job_id":"61a85e8d-b10b-4b8e-951c-6ea6697f8528","html_url":"https://github.com/WXinlong/ASIS","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/WXinlong%2FASIS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WXinlong%2FASIS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WXinlong%2FASIS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WXinlong%2FASIS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/WXinlong","download_url":"https://codeload.github.com/WXinlong/ASIS/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248666929,"owners_count":21142345,"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":["deep-learning","instance-segmentation","point-cloud","semantic-segmentation"],"created_at":"2024-10-14T12:09:51.137Z","updated_at":"2025-04-13T05:23:00.111Z","avatar_url":"https://github.com/WXinlong.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Associatively Segmenting Instances and Semantics in Point Clouds\n\nThe full paper is available at: https://arxiv.org/abs/1902.09852.\nQualitative results of ASIS on the S3DIS and vKITTI test fold:\n\n![](misc/s3dis_asis.png)\n![](misc/vkitti_asis.png)\n\n## Overview\n![](misc/fig.png)\n\n## Dependencies\n\nThe code has been tested with Python 2.7 on Ubuntu 14.04.\n*  [TensorFlow](https://www.tensorflow.org/)\n*  h5py\n\n\n\n## Data and Model\n\n* Download 3D indoor parsing dataset ([S3DIS Dataset](https://docs.google.com/forms/d/e/1FAIpQLScDimvNMCGhy_rmBA2gHfDu3naktRm6A8BPwAWWDv-Uhm6Shw/viewform?c=0\u0026w=1)). Version 1.2 of the dataset is used in this work.\n\n``` bash\npython collect_indoor3d_data.py\npython gen_h5.py\ncd data \u0026\u0026 python generate_input_list.py\ncd ..\n```\n\n* (optional) Trained model can be downloaded from [here](https://drive.google.com/open?id=1UF2nfXdWTOa1iXXmD54_c09rM7pr-kMK).\n\n## Usage\n\n* Compile TF Operators\n\n  Refer to [PointNet++](https://github.com/charlesq34/pointnet2)\n\n* Training\n``` bash\ncd models/ASIS/\nln -s ../../data .\nsh +x train.sh 5\n```\n\n* Evaluation\n``` bash\npython eval_iou_accuracy.py\n```\n\nNote: We test on Area5 and train on the rest folds in default. 6 fold CV can be conducted in a similar way.\n\n## Citation\nIf our work is useful for your research, please consider citing:\n\n\t@inproceedings{wang2019asis,\n\t\ttitle={Associatively Segmenting Instances and Semantics in Point Clouds},\n\t\tauthor={Wang, Xinlong and Liu, Shu and Shen, Xiaoyong and Shen, Chunhua, and Jia, Jiaya},\n\t\tbooktitle={CVPR},\n\t\tyear={2019}\n\t}\n\n\n## Acknowledgemets\nThis code largely benefits from following repositories:\n[PointNet++](https://github.com/charlesq34/pointnet2),\n[SGPN](https://github.com/laughtervv/SGPN),\n[DGCNN](https://github.com/WangYueFt/dgcnn) and\n[DiscLoss-tf](https://github.com/hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwxinlong%2Fasis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwxinlong%2Fasis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwxinlong%2Fasis/lists"}