{"id":13443952,"url":"https://github.com/hkust-vgd/riconv","last_synced_at":"2025-03-20T17:32:29.921Z","repository":{"id":113748470,"uuid":"204697348","full_name":"hkust-vgd/riconv","owner":"hkust-vgd","description":"Rotation Invariant Convolutions for 3D Point Clouds Deep Learning","archived":false,"fork":false,"pushed_at":"2019-09-14T02:21:38.000Z","size":39,"stargazers_count":57,"open_issues_count":3,"forks_count":9,"subscribers_count":6,"default_branch":"master","last_synced_at":"2024-10-28T07:41:57.193Z","etag":null,"topics":["convolution","point-clouds","rotation-invariant-convolutions","segments","tensorflow"],"latest_commit_sha":null,"homepage":"https://hkust-vgd.github.io/riconv/","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/hkust-vgd.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":"2019-08-27T12:23:00.000Z","updated_at":"2024-08-28T07:56:43.000Z","dependencies_parsed_at":null,"dependency_job_id":"56bcc0e0-cf35-4b03-94ee-385ea4792ff3","html_url":"https://github.com/hkust-vgd/riconv","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/hkust-vgd%2Friconv","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hkust-vgd%2Friconv/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hkust-vgd%2Friconv/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hkust-vgd%2Friconv/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hkust-vgd","download_url":"https://codeload.github.com/hkust-vgd/riconv/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244660707,"owners_count":20489383,"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":["convolution","point-clouds","rotation-invariant-convolutions","segments","tensorflow"],"created_at":"2024-07-31T03:02:14.831Z","updated_at":"2025-03-20T17:32:24.903Z","avatar_url":"https://github.com/hkust-vgd.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Rotation Invariant Convolutions for 3D Point Clouds Deep Learning\t\n\nZhiyuan Zhang, Binh-Son Hua, David W. Rosen, Sai-Kit Yeung\n\nInternational Conference on 3D Vision (3DV) 2019  \n\n## Introduction\nThis is the implementation of the rotation invariant convolution and neural networks for point clouds as shown in our paper. The key idea is to build rotation invariant features and use them to build a convolution to consume a point set. For details, please refer to our [project](https://hkust-vgd.github.io/riconv/).\n```\n@inproceedings{zhang-riconv-3dv19,\n    title = {Rotation Invariant Convolutions for 3D Point Clouds Deep Learning},\n    author = {Zhiyuan Zhang and Binh-Son Hua and David W. Rosen and Sai-Kit Yeung},\n    booktitle = {International Conference on 3D Vision (3DV)},\n    year = {2019}\n}\n```\n\n## Installation\nThe code is written in [TensorFlow](https://www.tensorflow.org/install/) and based on [PointNet](https://github.com/charlesq34/pointnet), [PointNet++](https://github.com/charlesq34/pointnet2), and [PointCNN](https://github.com/yangyanli/PointCNN). Please follow the instruction in [PointNet++](https://github.com/charlesq34/pointnet2) to compile the customized TF operators.  \n\nThe code has been tested with Python 3.6, TensorFlow 1.13.2, CUDA 10.0 and cuDNN 7.3 on Ubuntu 14.04.\n\n## Usage\n### Classification\nPlease download the preprocessed ModelNet40 dataset [here](https://shapenet.cs.stanford.edu/media/modelnet40_ply_hdf5_2048.zip).  \n\nTo train a network that takes XYZ coordinates as input to classify shapes in ModelNet40:\n```\npython3 train_val_cls.py\n```\nThe evaluation is performed after every training epoch.\n\n### Part Segmentation\nDownload the preprocessed ShapeNetPart dataset [here](https://shapenet.cs.stanford.edu/media/shapenetcore_partanno_segmentation_benchmark_v0_normal.zip).\n\nTo train a network that takes XYZ coordinates as input to segments object parts:\n```\npython train_val_seg.py\n```\nThe evaluation is performed after every training epoch.\n\n## License\nThis repository is released under MIT License (see LICENSE file for details).","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhkust-vgd%2Friconv","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhkust-vgd%2Friconv","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhkust-vgd%2Friconv/lists"}