{"id":26981759,"url":"https://github.com/visionxlab/pointobb-v3","last_synced_at":"2025-04-03T15:38:47.761Z","repository":{"id":273975646,"uuid":"920137724","full_name":"VisionXLab/PointOBB-v3","owner":"VisionXLab","description":"PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection","archived":false,"fork":false,"pushed_at":"2025-02-15T14:42:57.000Z","size":22371,"stargazers_count":17,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"two_stage","last_synced_at":"2025-02-15T15:30:59.865Z","etag":null,"topics":[],"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/VisionXLab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2025-01-21T16:20:06.000Z","updated_at":"2025-02-15T14:43:00.000Z","dependencies_parsed_at":"2025-02-03T14:47:08.779Z","dependency_job_id":"2966b99e-0bc0-43be-b302-8b5e274b05f4","html_url":"https://github.com/VisionXLab/PointOBB-v3","commit_stats":null,"previous_names":["zpywhu/pointobb-v3","visionxlab/pointobb-v3"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VisionXLab%2FPointOBB-v3","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VisionXLab%2FPointOBB-v3/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VisionXLab%2FPointOBB-v3/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VisionXLab%2FPointOBB-v3/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/VisionXLab","download_url":"https://codeload.github.com/VisionXLab/PointOBB-v3/tar.gz/refs/heads/two_stage","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247029409,"owners_count":20871883,"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":[],"created_at":"2025-04-03T15:38:47.188Z","updated_at":"2025-04-03T15:38:47.751Z","avatar_url":"https://github.com/VisionXLab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n \u003ch1 align=\"center\"\u003ePointOBB-v3： Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection\u003c/h1\u003e\n \u003cp align=\"center\"\u003e\n \u003ca href='https://scholar.google.com.hk/citations?user=rQbW67AAAAAJ\u0026hl' style='text-decoration: none' \u003ePeiyuan Zhang\u003c/a\u003e\u003csup\u003e\u003c/sup\u003e\u0026emsp;\n \u003ca href='https://scholar.google.com.hk/citations?hl=zh-CN\u0026user=6XibZaYAAAAJ' style='text-decoration: none' \u003eJunwei Luo\u003c/a\u003e\u003csup\u003e\u003c/sup\u003e\u0026emsp;\n \u003ca href='https://yangxue0827.github.io/' style='text-decoration: none' \u003eXue Yang\u003c/a\u003e\u003csup\u003e\u003c/sup\u003e\u0026emsp;\n \u003ca href='https://scholar.google.com/citations?user=OYtSc4AAAAAJ\u0026hl=en' style='text-decoration: none' \u003eYi Yu\u003c/a\u003e\u003csup\u003e\u003c/sup\u003e\u0026emsp; \n \u003ca href='https://scholar.google.com/citations?hl=en\u0026user=TvsTun4AAAAJ' style='text-decoration: none' \u003eQingyun Li\u003c/a\u003e\u003csup\u003e\u003c/sup\u003e\u0026emsp; \n \u003ca href='https://scholar.google.com.hk/citations?user=v-aQ8GsAAAAJ\u0026hl=zh-CN' style='text-decoration: none' \u003eYue Zhou\u003c/a\u003e\u003csup\u003e\u003c/sup\u003e\u0026emsp;\n \u003ca href='https://jiaxiaosong1002.github.io/' style='text-decoration: none' \u003eXiaosong Jia\u003c/a\u003e\u003csup\u003e\u003c/sup\u003e\u0026emsp;\n \u003ca href='https://scholar.google.com/citations?user=G9jWIggAAAAJ\u0026hl=en' style='text-decoration: none' \u003eXudong Lu\u003c/a\u003e\u003csup\u003e\u003c/sup\u003e\u0026emsp;\n \u003ca href='https://scholar.google.com/citations?user=8SCEv-YAAAAJ\u0026hl=en' style='text-decoration: none' \u003eJingdong Chen\u003c/a\u003e\u003csup\u003e\u003c/sup\u003e\u0026emsp;\n \u003ca href='https://scholar.google.com/citations?user=oamjJdYAAAAJ\u0026hl=zh-CN' style='text-decoration: none' \u003eXiang Li\u003c/a\u003e\u003csup\u003e\u003c/sup\u003e\u0026emsp;\n \u003ca href='https://scholar.google.com/citations?user=ga230VoAAAAJ\u0026hl=en' style='text-decoration: none' \u003eJunchi Yan\u003c/a\u003e\u003csup\u003e\u003c/sup\u003e\u0026emsp;\n \u003ca href='https://scholar.google.com/citations?user=wn9hc6UAAAAJ\u0026hl=zh-CN' style='text-decoration: none' \u003eYansheng Li\u003c/a\u003e\u003csup\u003e\u003c/sup\u003e\u0026emsp; \n \u003cdiv align=\"center\"\u003e\n \u003ca href='https://arxiv.org/abs/2501.13898'\u003e\u003cimg src='https://img.shields.io/badge/arXiv-2501.09720-brown.svg?logo=arxiv\u0026logoColor=white'\u003e\u003c/a\u003e\n\t \u003c/div\u003e\n \u003cp align='center'\u003e\n If you find our work helpful, please consider giving us a ⭐!\n \u003c/p\u003e\n \u003c/p\u003e\n\u003c/p\u003e\n\nThe paper is available at [PointOBB-v3](https://arxiv.org/abs/2501.13898). You are also welcome to check out the conference version [PointOBB](https://openaccess.thecvf.com/content/CVPR2024/html/Luo_PointOBB_Learning_Oriented_Object_Detection_via_Single_Point_Supervision_CVPR_2024_paper.html).\n\n**📌 Note: This branch contains the code for the two-stage version. For the end-to-end version, please refer to [`end-to-end`](https://github.com/VisionXLab/PointOBB-v3/tree/end_to_end) branch.**\n\n\u003cimg width=\"989\" alt=\"image\" src=\"https://github.com/user-attachments/assets/e320a8ce-6c98-438b-9b92-0c922536b5ab\" /\u003e\n\n### Train/Test\nPlease see [`PointOBB/README.md`](PointOBB/README.md).\n\n\n### Weight\n\nDIOR-R\n\n| Backbone | mAP | Angle | Config | Detector | Download |\n| :----------------------: | :---: | :---: | :---: | :------: | :------------------------------------------------------------------------------------------------------------: |\n| ResNet50 (1024,1024,200) | 41.82 | le90 | [pointobbv3-dior](PointOBB/configs2/pointobb/pointobbv3_r50_fpn_2x_dior_two_stage.py)| Oriented RCNN | [model](https://drive.google.com/file/d/1ZqBQivJ19QFA-VVCRaYAOuPkgA8PtjNA/view?usp=sharing) |\n\n\nDOTA-v1.0\n\n| Backbone | mAP | Angle | Config | Detector | Download |\n| :----------------------: | :---: | :---: | :-----: | :------: | :------------------------------------------------------------------------------------------------------------: |\n| ResNet50 (1024,1024,200) | 50.44 | le90 | [pointobbv3-dota](PointOBB/configs2/pointobb/pointobbv3_r50_fpn_2x_dota_two_stage.py)| Oriented RCNN | [model](https://drive.google.com/file/d/1bFhYBdIMy6yBCyAmTVHcZP6UD3w9cbx8/view?usp=sharing) |\n\n\nDOTA-v1.5\n\n| Backbone | mAP | Angle | Config | Detector | Download |\n| :----------------------: | :---: | :---: | :-----: | :------: | :------------------------------------------------------------------------------------------------------------: |\n| ResNet50 (1024,1024,200) | 38.08 | le90 | [pointobbv3-dota15](PointOBB/configs2/pointobb/pointobbv3_r50_fpn_2x_dota15_two_stage.py)| Oriented RCNN | [model](https://drive.google.com/file/d/1bHMmClalEtupq4CJ-6sZBfqW6RfTLEqF/view?usp=sharing) |\n\n\nDOTA-v2.0\n\n| Backbone | mAP | Angle | Config | Detector | Download |\n| :----------------------: | :---: | :---: | :-----: | :------: | :------------------------------------------------------------------------------------------------------------: |\n| ResNet50 (1024,1024,200) | 24.86 | le90 | [pointobbv3-dota20](PointOBB/configs2/pointobb/pointobbv3_r50_fpn_2x_dota20_two_stage.py)| Oriented RCNN | [model](https://drive.google.com/file/d/1u__zL9CXyGyeAZVq9hQF-r1qhduzUG0C/view?usp=sharing) |\n\nFAIR1M\n\n| Backbone | mAP | Angle | Config | Detector | Download |\n| :----------------------: | :---: | :---: | :-----: | :------: | :------------------------------------------------------------------------------------------------------------: |\n| ResNet50 (1024,1024,200) | 20.19 | le90 | [pointobbv3-fair](PointOBB/configs2/pointobb/pointobbv3_r50_fpn_2x_fair_two_stage.py)| Oriented RCNN | [model](https://drive.google.com/file/d/1atuyx7-aZYSOndPkhpr7_4ygDmQNEWuq/view?usp=sharing) |\n\n\nSTAR\n\n| Backbone | mAP | Angle | Config | Detector | Download |\n| :----------------------: | :---: | :---: | :-----: | :------: | :------------------------------------------------------------------------------------------------------------: |\n| ResNet50 (1024,1024,200) | 16.73 | le90 | [pointobbv3-star](PointOBB/configs2/pointobb/pointobbv3_r50_fpn_2x_star_two_stage.py)| Oriented RCNN | [model](https://drive.google.com/file/d/1m4NAIdTv5vBf9b_4DAJBETRjQw79khZ6/view?usp=sharing) |\n\n\nRSAR\n\n| Backbone | mAP | Angle | Config | Detector | Download |\n| :----------------------: | :---: | :---: | :-----: | :------: | :------------------------------------------------------------------------------------------------------------: |\n| ResNet50 (1024,1024,200) | 22.84 | le90 | [pointobbv3-rsar](PointOBB/configs2/pointobb/pointobbv3_r50_fpn_2x_rsar_two_stage.py)| Oriented RCNN | [model](https://drive.google.com/file/d/1bf4wzAApTUFm05sRXmXSyOWzrohW4wx-/view?usp=sharing) |\n\n### Citation\nIf you find this work helpful, please consider to cite:\n```\n@article{zhang2025pointobb,\n title = {PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection},\n author = {Zhang, Peiyuan and Luo, Junwei and Yang, Xue and Yu, Yi and Li, Qingyun and Zhou, Yue and Jia, Xiaosong and Lu, Xudong and Chen, Jingdong and Li, Xiang and others},\n journal = {arXiv preprint arXiv:2501.13898},\n year = {2025}\n}\n```\n```\n@InProceedings{luo2024pointobb,\n title = {PointOBB: Learning Oriented Object Detection via Single Point Supervision},\n author = {Luo, Junwei and Yang, Xue and Yu, Yi and Li, Qingyun and Yan, Junchi and Li, Yansheng},\n booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},\n pages = {16730-16740},\n year = {2024}\n}\n```\n\n-----\n\nSpecial thanks to the codebase contributors of MMRotate and P2BNet!\n```\n@inproceedings{zhou2022mmrotate,\n title = {MMRotate: A Rotated Object Detection Benchmark using PyTorch},\n author = {Zhou, Yue and Yang, Xue and Zhang, Gefan and Wang, Jiabao and Liu, Yanyi and\n Hou, Liping and Jiang, Xue and Liu, Xingzhao and Yan, Junchi and Lyu, Chengqi and\n Zhang, Wenwei and Chen, Kai},\n booktitle={Proceedings of the 30th ACM International Conference on Multimedia},\n year={2022}\n}\n```\n\n```\n@inproceedings{P2BNet,\n title = {Point-to-Box Network for Accurate Object Detection via Single Point Supervision},\n author = {Pengfei Chen, Xuehui Yu, Xumeng Han, Najmul Hassan, Kai Wang, Jiachen Li, Jian Zhao, Humphrey Shi, Zhenjun Han, and Qixiang Ye},\n booktitle = {ECCV},\n year = {2022}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvisionxlab%2Fpointobb-v3","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvisionxlab%2Fpointobb-v3","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvisionxlab%2Fpointobb-v3/lists"}