{"id":13443651,"url":"https://github.com/CVMI-Lab/ST3D","last_synced_at":"2025-03-20T17:30:57.675Z","repository":{"id":37739202,"uuid":"344459273","full_name":"CVMI-Lab/ST3D","owner":"CVMI-Lab","description":"(CVPR 2021 \u0026  T-PAMI 2022) ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection \u0026 ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection","archived":false,"fork":false,"pushed_at":"2024-07-14T13:06:36.000Z","size":2441,"stargazers_count":297,"open_issues_count":5,"forks_count":46,"subscribers_count":13,"default_branch":"master","last_synced_at":"2024-10-28T07:39:37.152Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CVMI-Lab.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-03-04T12:00:57.000Z","updated_at":"2024-10-05T09:12:38.000Z","dependencies_parsed_at":"2024-01-18T14:48:07.648Z","dependency_job_id":"0a4f1bf8-264e-43a4-9ac4-940ebfeac842","html_url":"https://github.com/CVMI-Lab/ST3D","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/CVMI-Lab%2FST3D","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CVMI-Lab%2FST3D/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CVMI-Lab%2FST3D/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CVMI-Lab%2FST3D/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CVMI-Lab","download_url":"https://codeload.github.com/CVMI-Lab/ST3D/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244660252,"owners_count":20489306,"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":"2024-07-31T03:02:06.273Z","updated_at":"2025-03-20T17:30:56.339Z","avatar_url":"https://github.com/CVMI-Lab.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# ST3D \u0026 ST3D++\n\nCode release for the paper **ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection**, CVPR 2021 and\n**ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection**, T-PAMI 2022.\n\n\n## News\n[2023-05-17] Support Waymo -\u003e Lyft setting.\n\n[2022-09-26] ST3D++ (The extension of ST3D) has been integrated in this repo for Waymo-\u003eKITTI and nuScenes-\u003eKITTI.\n\n\n## Introduction\nOur code is based on OpenPCDet v0.3.0.\nMore updates on OpenPCDet are supposed to be compatible with our code.\n\n## Model Zoo\n\n### Waymo -\u003e KITTI TASK\n\n|                                                                                             |     method     | Car@R40 | Ped@R40 | Cyc@R40 | \n|---------------------------------------------------------------------------------------------|:--------------:|:-------:|:-------:|:-------:|\n| [SECOND-IoU](tools/cfgs/da-waymo-kitti_models/secondiou_st3d/secondiou_st3d_car.yaml)       |      ST3D      |  62.19  |  48.33  |  46.09  | \n| [SECOND-IoU](tools/cfgs/da-waymo-kitti_models/secondiou_st3d/secondiou_st3d_car.yaml)       |  ST3D (w/ sn)  |  73.62  |  51.92  |  53.00  |\n| [SECOND-IoU](tools/cfgs/da-waymo-kitti_models/secondiou_st3d/secondiou_st3d++_ros_car.yaml) |     ST3D++     |  65.10  |  53.87  |  53.43  |\n| [SECOND-IoU](tools/cfgs/da-waymo-kitti_models/secondiou_st3d/secondiou_st3d++_sn_car.yaml)  | ST3D++ (w/ sn) |  74.73  |  59.21  |  60.76  |\n| [PVRCNN](tools/cfgs/da-waymo-kitti_models/pvrcnn_st3d/pvrcnn_st3d.yaml)                     |      ST3D      |  64.05  |    -    |    -    |\n| [PVRCNN](tools/cfgs/da-waymo-kitti_models/pvrcnn_st3d/pvrcnn_st3d.yaml)                     |  ST3D (w/ sn)  |  77.33  |    -    |    -    |\n\nWe could not provide the above pretrained models due to [Waymo Dataset License Agreement](https://waymo.com/open/terms/), \nbut you should achieve similar performance by training with the default configs. To access these pretrained models, please \nsend us an email with your name, institute, a screenshot of the Waymo dataset registration confirmation mail, and your \nintended usage. Please send a second email if we don't get back to you in two days. Please note that Waymo open dataset is \nunder strict non-commercial license, so we are not allowed to share the model with you if it will use for any profit-oriented activities.\n\nAlso, the training Waymo data used in our work is version 1.0, but the version now available is version 1.2. \nThe pretrained model on these two version data should be similar when adapted to KITTI.  \n\n\n### nuScenes -\u003e KITTI TASK\n|                                                                                                |     method     | Car@R40 | Ped@R40 | Cyc@R40 | \n|------------------------------------------------------------------------------------------------|:--------------:|:-------:|:-------:|:-------:|\n| [SECOND-IoU](tools/cfgs/da-nuscenes-kitti_models/secondiou/secondiou_old_anchor.yaml)          |  Source Only   |  17.92  |    -    |    -    | \n| [SECOND-IoU](tools/cfgs/da-nuscenes-kitti_models/secondiou/secondiou_old_anchor_ros.yaml)      |      ROS       |  25.37  |    -    |    -    | \n| [SECOND-IoU](tools/cfgs/da-nuscenes-kitti_models/secondiou/secondiou_old_anchor_sn.yaml)       |       SN       |  21.23  |  34.36  |  5.67   |\n| [SECOND-IoU](tools/cfgs/da-nuscenes-kitti_models/secondiou_st3d/secondiou_st3d_car.yaml)       |      ST3D      |  55.19  |    -    |    -    |\n| [SECOND-IoU](tools/cfgs/da-nuscenes-kitti_models/secondiou_st3d/secondiou_st3d_car.yaml)       |  ST3D (w/ SN)  |  62.27  |    -    |    -    |\n| [SECOND-IoU](tools/cfgs/da-nuscenes-kitti_models/secondiou_st3d/secondiou_st3d++_ros_car.yaml) |     ST3D++     |  66.01  |  45.23  |  25.98  |\n| [SECOND-IoU](tools/cfgs/da-nuscenes-kitti_models/secondiou_st3d/secondiou_st3d++_sn_car.yaml)  | ST3D++ (w/ SN) |  66.24  |  46.75  |  22.66  |\n| [PV-RCNN](tools/cfgs/da-nuscenes-kitti_models/pvrcnn/pvrcnn_old_anchor.yaml)                   |  Source Only   |  37.17  |    -    |    -    |\n| [PV-RCNN](tools/cfgs/da-nuscenes-kitti_models/pvrcnn/pvrcnn_old_anchor_ros.yaml)               |      ROS       |  38.84  |    -    |    -    | \n| [PV-RCNN](tools/cfgs/da-nuscenes-kitti_models/pvrcnn/pvrcnn_old_anchor_sn.yaml)                |       SN       |  49.47  |    -    |    -    |\n| [PV-RCNN](tools/cfgs/da-nuscenes-kitti_models/pvrcnn_st3d/pvrcnn_st3d.yaml)                    |      ST3D      |  71.11  |    -    |    -    | \n| [PV-RCNN](tools/cfgs/da-nuscenes-kitti_models/pvrcnn_st3d/pvrcnn_st3d.yaml)                    |  ST3D (w/ SN)  |  73.16  |    -    |    -    |\n| [PointRCNN](tools/cfgs/da-nuscenes-kitti_models/pointrcnn/pointrcnn.yaml)                      |      ROS       |  55.92  |    -    |    -    |\n| [PointRCNN](tools/cfgs/da-nuscenes-kitti_models/pointrcnn_st3d/pointrcnn_st3d++_car.yaml)      |    ST3D++      |  67.51  |    -    |    -    |\n\nWe provide pretrained models here for nuScenes \u003e KITTI task in [models](https://connecthkuhk-my.sharepoint.com/:f:/g/personal/jhyang13_connect_hku_hk/ErVtcVax3OBJgn4TyQxbOwMBCt1kDCt4_rYaXqHPsg_ZNw?e=a42lgy).\n\n\n### Waymo -\u003e nuScenes TASK\n|                                             | method | Car@R11 | Car@R40 | download | \n|---------------------------------------------|----------:|:-------:|:-------:|:---------:|\n| [SECOND-IoU](tools/cfgs/da-waymo-nus_models/secondiou_st3d/secondiou_st3d.yaml) | ST3D | 23.24 | 20.19 | [model](https://connecthkuhk-my.sharepoint.com/:u:/g/personal/jhyang13_connect_hku_hk/EeMq80RN8K1Fsub3qWyfexMB5mIgb-eohHbs9iCMlTY9Pw?e=7ClPTt) | \n| [PVRCNN](tools/cfgs/da-waymo-nus_models/pvrcnn_st3d/pvrcnn_st3d.yaml)    | ST3D | 27.18 | 22.99 | [model](https://connecthkuhk-my.sharepoint.com/:u:/g/personal/jhyang13_connect_hku_hk/Eevtjh6MnKlBkptG3Hh_jyUBkunmyedmXbahmBf0CpUqpw?e=JM31IH) |\n| [SECOND-IoU](tools/cfgs/da-waymo-nus_models/secondiou_st3d/secondiou_st3d.yaml) | ST3D (w/ sn) | 23.52 | 20.38 | [model](https://connecthkuhk-my.sharepoint.com/:u:/g/personal/jhyang13_connect_hku_hk/ETLk3FQu_5VPqghADqPA8CcB6uLJtWRLuCaIryCs3Ps7Uw?e=a2iQVb) | \n| [PVRCNN](tools/cfgs/da-waymo-nus_models/pvrcnn_st3d/pvrcnn_st3d.yaml)    | ST3D (w/ sn)   | 28.06 | 23.67 | [model](https://connecthkuhk-my.sharepoint.com/:u:/g/personal/jhyang13_connect_hku_hk/EZdecJDPWhhHpflKBuwJhjIBLq23eGcxyzY1sfFKHn9zlA?e=6ZbFOM) |\n\nWe could not provide the above pretrained models due to [Waymo Dataset License Agreement](https://waymo.com/open/terms/), \nbut you should achieve similar performance by training with the default configs.\n\n\n### Waymo -\u003e Lyft TASK\n|                                                                                  |       method | Car@R11 | Car@R40 |                                            download                                            | \n|----------------------------------------------------------------------------------|-------------:|:-------:|:-------:|:----------------------------------------------------------------------------------------------:|\n| [SECOND-IoU](tools/cfgs/da-waymo-lyft_models/secondiou/secondiou.yaml)           |  Source Only |    -    |  54.34  |                                               -                                                | \n| [SECOND-IoU](tools/cfgs/da-waymo-lyft_models/secondiou/secondiou_sn.yaml)        |           SN |    -    |  54.34  |                                               -                                                |\n| [SECOND-IoU](tools/cfgs/da-waymo-lyft_models/secondiou_st3d/secondiou_st3d.yaml) |         ST3D |    -    |  59.24  | [model](https://drive.google.com/file/d/1YfOawQUvdVmExQ5H_-xQuFBCFg57dD01/view?usp=share_link) | \n| [SECOND-IoU](tools/cfgs/da-waymo-lyft_models/secondiou_st3d/secondiou_st3d.yaml) | ST3D (w/ sn) |    -    |  57.99  | [model](https://drive.google.com/file/d/1bZQaDeIxcUzk6fyMI7RRykl-eAnpySCp/view?usp=share_link) | \n| [PVRCNN](tools/cfgs/da-waymo-lyft_models/pvrcnn/pvrcnn.yaml)                     |  Source Only |    -    |  58.53  |                                               -                                                |\n| [PVRCNN](tools/cfgs/da-waymo-lyft_models/pvrcnn/pvrcnn_sn.yaml)                  |           SN |    -    |  56.64  |                                               -                                                |\n| [PVRCNN](tools/cfgs/da-waymo-lyft_models/pvrcnn_st3d/pvrcnn_st3d.yaml)           |         ST3D |    -    |  60.53  | [model](https://drive.google.com/file/d/12hVyBwT3rT3bm6yWsa5xrBim89iPVkev/view?usp=share_link) |\n| [PVRCNN](tools/cfgs/da-waymo-lyft_models/pvrcnn_st3d/pvrcnn_st3d.yaml)           | ST3D (w/ sn) |    -    |  58.54  | [model](https://drive.google.com/file/d/1fYbD_43vGQYaCY767L78-2Znyber5tdf/view?usp=share_link) |\n\nWe could not provide the above pretrained models due to [Waymo Dataset License Agreement](https://waymo.com/open/terms/), \nbut you should achieve similar performance by training with the default configs.\n\n\n\n## Installation\n\nPlease refer to [INSTALL.md](docs/INSTALL.md) for the installation.\n\n## Getting Started\n\nPlease refer to [GETTING_STARTED.md](docs/GETTING_STARTED.md) to learn more usage about this project.\n\n### Supported features and ToDo List\n\n- [x] Support inference and pre-trained model \n\n- [x] Support training code on Waymo -\u003e KITTI task\n\n- [x] Update to OpenPCDet v0.3.0 version.\n  \n- [x] Support more adaptation tasks.\n\n## License\n\nOur code is released under the Apache 2.0 license.\n\n## Acknowledgement\n\nOur code is heavily based on [OpenPCDet v0.3](https://github.com/open-mmlab/OpenPCDet/commit/e3bec15f1052b4827d942398f20f2db1cb681c01). Thanks OpenPCDet Development Team for their awesome codebase.\n\n## Citation\n\nIf you find this project useful in your research, please consider cite:\n```\n@inproceedings{yang2021st3d,\n    title={ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection},\n    author={Yang, Jihan and Shi, Shaoshuai and Wang, Zhe and Li, Hongsheng and Qi, Xiaojuan},\n    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},\n    year={2021}\n}\n```\n```\n@article{yang2021st3d++,\n  title={ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection},\n  author={Yang, Jihan and Shi, Shaoshuai and Wang, Zhe and Li, Hongsheng and Qi, Xiaojuan},\n  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},\n  year={2022}\n}\n```\n```\n@misc{openpcdet2020,\n    title={OpenPCDet: An Open-source Toolbox for 3D Object Detection from Point Clouds},\n    author={OpenPCDet Development Team},\n    howpublished = {\\url{https://github.com/open-mmlab/OpenPCDet}},\n    year={2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCVMI-Lab%2FST3D","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FCVMI-Lab%2FST3D","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCVMI-Lab%2FST3D/lists"}