{"id":21322757,"url":"https://github.com/qingyonghu/sqn","last_synced_at":"2025-07-12T05:31:08.436Z","repository":{"id":43692082,"uuid":"356267316","full_name":"QingyongHu/SQN","owner":"QingyongHu","description":"SQN in Tensorflow (ECCV'2022)","archived":false,"fork":false,"pushed_at":"2023-04-27T09:44:03.000Z","size":13267,"stargazers_count":102,"open_issues_count":20,"forks_count":10,"subscribers_count":14,"default_branch":"main","last_synced_at":"2024-10-28T05:59:56.112Z","etag":null,"topics":["annotations","computer-vision","deep-learning","point-cloud","weakly-supervised-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/QingyongHu.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":"2021-04-09T12:43:24.000Z","updated_at":"2024-10-18T13:17:39.000Z","dependencies_parsed_at":"2024-01-18T14:41:20.158Z","dependency_job_id":"a4e6ba86-8ab4-4fac-9285-36d9bf751046","html_url":"https://github.com/QingyongHu/SQN","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/QingyongHu%2FSQN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QingyongHu%2FSQN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QingyongHu%2FSQN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QingyongHu%2FSQN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/QingyongHu","download_url":"https://codeload.github.com/QingyongHu/SQN/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225795327,"owners_count":17525325,"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":["annotations","computer-vision","deep-learning","point-cloud","weakly-supervised-segmentation"],"created_at":"2024-11-21T20:17:58.546Z","updated_at":"2024-11-21T20:17:59.224Z","avatar_url":"https://github.com/QingyongHu.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![arXiv](https://img.shields.io/badge/arXiv-2104.04891-b31b1b.svg)](https://arxiv.org/abs/2104.04891)\n[![GitHub Stars](https://img.shields.io/github/stars/QingyongHu/SQN?style=social)](https://github.com/QingyongHu/SQN)\n![visitors](https://visitor-badge.glitch.me/badge?page_id=QingyongHu/SQN)\n[![License CC BY-NC-SA 4.0](https://img.shields.io/badge/license-CC4.0-blue.svg)](https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode)\n\n# SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds (ECCV2022)\n\nThis is the official repository of the **Semantic Query Network (SQN)**. For technical details, please refer to:\n\n**SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds** \u003cbr /\u003e\n[Qingyong Hu](https://qingyonghu.github.io/), [Bo Yang](https://yang7879.github.io/), [Guangchi Fang]()\n, [Ales Leonardis](https://www.cs.bham.ac.uk/~leonarda/),\n[Yulan Guo](http://yulanguo.me/), [Niki Trigoni](https://www.cs.ox.ac.uk/people/niki.trigoni/)\n, [Andrew Markham](https://www.cs.ox.ac.uk/people/andrew.markham/). \u003cbr /\u003e\n**[[Paper](https://arxiv.org/abs/2104.04891)] [[Video](https://youtu.be/Q6wICSRRw3s)]** \u003cbr /\u003e\n\n### (1) Setup\n\nThis code has been tested with Python 3.5, Tensorflow 1.11, CUDA 9.0 and cuDNN 7.4.1 on Ubuntu 16.04/Ubuntu 18.04.\n\n- Clone the repository\n\n```\ngit clone --depth=1 https://github.com/QingyongHu/SQN \u0026\u0026 cd SQN\n```\n\n- Setup python environment\n\n```\nconda create -n sqn python=3.5\nsource activate sqn\npip install -r helper_requirements.txt\nsh compile_op.sh\n```\n\n### (2) Training (Semantic3D as example)\n\nFirst, follow the RandLA-Net [instruction](https://github.com/QingyongHu/RandLA-Net) to prepare the dataset, and then\nmanually change the\ndataset [path](https://github.com/QingyongHu/SQN/blob/f75eb51532a5319c0da5320c20f58fbe5cb3bbcd/main_Semantic3D.py#L17) here.\n\n- Start training with weakly supervised setting:\n```\npython main_Semantic3D.py --mode train --gpu 0 --labeled_point 0.1%\n```\n- Evaluation:\n```\npython main_Semantic3D.py --mode test --gpu 0 --labeled_point 0.1%\n```\n\nQuantitative results achieved by our SQN:\n\n| ![2](imgs/Semantic3D.gif)   | ![z](imgs/SensatUrban.gif) |\n| ------------------------------ | ---------------------------- |\n| ![2](imgs/Toronto3D.gif)   | ![z](imgs/S3DIS.gif) |\n\n### (3) Sparse Annotation Demo\n\n\u003cp align=\"center\"\u003e \u003ca href=\"https://youtu.be/N0UAeY31msY\"\u003e\u003cimg src=\"imgs/Demo_cover.png\" width=\"70%\"\u003e\u003c/a\u003e \u003c/p\u003e\n\n\n### Citation\n\nIf you find our work useful in your research, please consider citing:\n\n\t@inproceedings{hu2021sqn,\n      title={SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds},\n      author={Hu, Qingyong and Yang, Bo and Fang, Guangchi and Guo, Yulan and Leonardis, Ales and Trigoni, Niki and Markham, Andrew},\n      booktitle={European Conference on Computer Vision},\n      year={2022}\n    }\n\n## Related Repos\n\n1. [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://github.com/QingyongHu/RandLA-Net) ![GitHub stars](https://img.shields.io/github/stars/QingyongHu/RandLA-Net.svg?style=flat\u0026label=Star)\n2. [SoTA-Point-Cloud: Deep Learning for 3D Point Clouds: A Survey](https://github.com/QingyongHu/SoTA-Point-Cloud) ![GitHub stars](https://img.shields.io/github/stars/QingyongHu/SoTA-Point-Cloud.svg?style=flat\u0026label=Star)\n3. [3D-BoNet: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds](https://github.com/Yang7879/3D-BoNet) ![GitHub stars](https://img.shields.io/github/stars/Yang7879/3D-BoNet.svg?style=flat\u0026label=Star)\n4. [SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration](https://github.com/QingyongHu/SpinNet) ![GitHub stars](https://img.shields.io/github/stars/QingyongHu/SpinNet.svg?style=flat\u0026label=Star)\n5. [SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds](https://github.com/QingyongHu/SensatUrban) ![GitHub stars](https://img.shields.io/github/stars/QingyongHu/SensatUrban.svg?style=flat\u0026label=Star)\n6. [Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds](https://github.com/yifanzhang713/IA-SSD) ![GitHub stars](https://img.shields.io/github/stars/yifanzhang713/IA-SSD.svg?style=flat\u0026label=Star)\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqingyonghu%2Fsqn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fqingyonghu%2Fsqn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqingyonghu%2Fsqn/lists"}