{"id":21384657,"url":"https://github.com/imoonlab/pvrnet","last_synced_at":"2025-09-13T08:36:12.839Z","repository":{"id":111912321,"uuid":"196833424","full_name":"iMoonLab/PVRNet","owner":"iMoonLab","description":"PVRNet: Point-View Relation Neural Network for 3D Shape Recognition (AAAI 2019)","archived":false,"fork":false,"pushed_at":"2019-07-15T02:17:57.000Z","size":211,"stargazers_count":47,"open_issues_count":3,"forks_count":8,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-07-13T14:41:17.205Z","etag":null,"topics":["3d-shape-recognition","deep-learning","multi-view","point-cloud","pytorch"],"latest_commit_sha":null,"homepage":null,"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/iMoonLab.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}},"created_at":"2019-07-14T12:23:46.000Z","updated_at":"2024-11-11T15:38:49.000Z","dependencies_parsed_at":null,"dependency_job_id":"a04b1d8c-9365-4164-b3ea-b6fc3a206503","html_url":"https://github.com/iMoonLab/PVRNet","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/iMoonLab/PVRNet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FPVRNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FPVRNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FPVRNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FPVRNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iMoonLab","download_url":"https://codeload.github.com/iMoonLab/PVRNet/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FPVRNet/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274939377,"owners_count":25377789,"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","status":"online","status_checked_at":"2025-09-13T02:00:10.085Z","response_time":70,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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-shape-recognition","deep-learning","multi-view","point-cloud","pytorch"],"created_at":"2024-11-22T11:42:27.157Z","updated_at":"2025-09-13T08:36:12.788Z","avatar_url":"https://github.com/iMoonLab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PVRNet\nPVRNet: Point-View Relation Neural Network for 3D Shape Recognition (AAAI 2019)\n\nCreated by Haoxuan You, Yifan Feng, Xibin Zhao, Changqing Zou, Rongrong Ji, Yue Gao from Tsinghua University.\n\n![](https://github.com/iMoonLab/PVRNet/blob/master/docs/pipeline.png)\n### Introduction\nThis work will appear in AAAI 2019. We propose a point-view relation neural network called PVRNet for 3D shape recognition and retrieval. You can chekc our [paper](https://arxiv.org/abs/1812.00333) for more details.\n\nIn this repository, our code and data are released for training our PVRNet on ModelNet40 dataset.\n\n### Citation\nIf you find our work useful in your research, please cite our paper:\n```\n@article{you2018pvrnet,\ntitle={PVRNet: Point-View Relation Neural Network for 3D Shape Recognition},\nauthor={You, Haoxuan and Feng, Yifan and Zhao, Xibin and Zou, Changqing and Ji, Rongrong and Gao, Yue},\njournal={AAAI 2019},\nyear={2018}\n}\n```\n### Configuration\nCode is tested under the environment of Pytorch 0.4.1, Python 3.6 and CUDA 9.0 on Ubuntu 16.04. \n\nData: [point cloud data](https://drive.google.com/file/d/1DUh_8PQjh3ds4yO0O8q_vb0HPistOJ4y/view?usp=sharing) and [multi-view(12-view) data](https://drive.google.com/file/d/12JbIPLvcSUsMjxb_CZYXI8xQK2UKosio/view?usp=sharing) from ModelNet40 dataset.\n\nPretrained Model: [multi-view part(MVCNN)](https://drive.google.com/file/d/1dZG7XojtPS9Cl5aaH4iWXA_N2PximB6i/view?usp=sharing), [point cloud part(DGCNN)](https://drive.google.com/file/d/1fY9E44xuPwUFxJ_BIeP5NXwrB7DQm1tw/view?usp=sharing) and [PVRNet](https://drive.google.com/file/d/1g3Ef68jRSY2mNf54dOeqNFYZTm4cO13d/view?usp=sharing)  \n\n### Usage\n+ Download data and pretrained ckpt from above links. Create dir for data as well as result, and place them under corresponding dirs(./data/ and ./result/ckpt/).\n\n    ```mkdir -p data result/ckpt```\n    \n+ Train PVRNet. This would use pretrained MVCNN model and DGCNN model saved in ./result/ckpt:\n\n    ``` python train_pvrnet.py```\n\n+ If validate the performance of PVRNet with our pretrained model:\n\n    `python val_pvrnet.py`\n\n    If validate the performance of pretrained MVCNN and DGCNN models:\n    ```\n    python val_mvcnn.py\n    python val_pc.py\n    ```\n\n+ If you want to train new model for MVCNN and DGCNN:\n\n    \n    ```\n    python train_mvcnn.py\n    python train_pc.py\n    ```\n\n\n### License\nOur code is released under MIT License (see LICENSE file for details).\n\n\n    \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimoonlab%2Fpvrnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fimoonlab%2Fpvrnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimoonlab%2Fpvrnet/lists"}