{"id":13441046,"url":"https://github.com/detectRecog/ZoomNet","last_synced_at":"2025-03-20T11:34:53.410Z","repository":{"id":111966386,"uuid":"221625599","full_name":"detectRecog/ZoomNet","owner":"detectRecog","description":"ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection","archived":false,"fork":false,"pushed_at":"2020-05-11T03:15:28.000Z","size":3,"stargazers_count":67,"open_issues_count":1,"forks_count":6,"subscribers_count":20,"default_branch":"master","last_synced_at":"2024-08-01T03:32:50.331Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/detectRecog.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}},"created_at":"2019-11-14T06:14:49.000Z","updated_at":"2024-01-04T16:39:34.000Z","dependencies_parsed_at":"2023-03-24T23:47:53.826Z","dependency_job_id":null,"html_url":"https://github.com/detectRecog/ZoomNet","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/detectRecog%2FZoomNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/detectRecog%2FZoomNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/detectRecog%2FZoomNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/detectRecog%2FZoomNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/detectRecog","download_url":"https://codeload.github.com/detectRecog/ZoomNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221752225,"owners_count":16874949,"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":"2024-07-31T03:01:29.250Z","updated_at":"2024-10-28T00:31:39.725Z","avatar_url":"https://github.com/detectRecog.png","language":null,"funding_links":[],"categories":["Others"],"sub_categories":[],"readme":"# ZoomNet(AAAI2020 oral)\nThis is the repository for paper \"ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection\".\n\nThe pixel-wise annotations on the KITTI trainval set is available via:\n - [Google Drive trainset](https://drive.google.com/open?id=1vqSrOiwojYiGwuw5wympxw_PC448g6Zf) , [Google Drive valset](https://drive.google.com/open?id=1D79oIocq2hYTtJn3xzH1Iz-yW32CyIZL) \n \n - [BaiduYun Drive trainset (code: ljhj)](https://pan.baidu.com/s/1Bp0ulfCm6RYvQ770U1V6Eg), [BaiduYun Drive valset (code: kwxf)](https://pan.baidu.com/s/1GMbhj9oHtgqTqij36Acksg)\n\n\nSample code for processing the provided annotations.\n```python\nimport pickle\nimport numpy as np\n\ndef load_pickle(filename):\n    with open(filename, 'rb') as f:\n        obj = pickle.load(f)\n    return obj\n\ninfo = load_pickle(‘000002.pkl) # info.keys(): dict_keys(['data_idx', 'objects', 'calib', 'imw', 'imh', 'instL', 'instR’]). ‘InstL’ contains the pixel-wise inst_id(1-channel), depth(1-channel), part location (3-channel).\n# sample code for pixel-wise depth annotation\npkl_objects = info['objects']\ncalib = info['calib']\nf = calib['P'][0, 0]\nbl = (calib['P'][0, 3] - calib['P3'][0, 3]) / f\nf_bl = f * bl\ninst_map_left_ = np.concatenate([np.expand_dims(el.toarray(), -1) for el in info['instL']], axis=-1)\n# convert depth to disp\ndispMapL = f_bl / inst_map_left_[:, :, 1].copy()\ndispMapL[np.isinf(dispMapL)] = 0\nprint(dispMap.shape)\n```\n\nThe code for generating pixel-wise annotations and ZoomNet (pytorch) needs to be organised before release. A version on paddle-paddle is also expected to be released. However, I’m currently working on a workshop on CVPR and thus delayed the release of code. I'm sorry about that.\n\nIf you are benefited from this paper, please cite our paper as follows:\n\n```\n@inproceedings{xu2020zoomnet,\n  title={ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection},\n  author={Xu, Zhenbo and Zhang, Wei and Ye, Xiaoqing and Tan, Xiao and Yang, Wei and Wen, Shilei and Ding, Errui and Meng, Ajin and Huang, Liusheng},\n  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},\n  volume={2},\n  pages={7},\n  year={2020}\n}\n```\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FdetectRecog%2FZoomNet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FdetectRecog%2FZoomNet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FdetectRecog%2FZoomNet/lists"}