{"id":13443628,"url":"https://github.com/TRAILab/CaDDN","last_synced_at":"2025-03-20T17:30:46.340Z","repository":{"id":50441894,"uuid":"329635967","full_name":"TRAILab/CaDDN","owner":"TRAILab","description":"Categorical Depth Distribution Network for Monocular 3D Object Detection (CVPR 2021 Oral)","archived":false,"fork":false,"pushed_at":"2022-12-24T14:23:24.000Z","size":548017,"stargazers_count":367,"open_issues_count":23,"forks_count":62,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-10-28T07:39:29.478Z","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/TRAILab.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}},"created_at":"2021-01-14T14:16:22.000Z","updated_at":"2024-10-14T06:51:29.000Z","dependencies_parsed_at":"2023-01-30T21:00:53.065Z","dependency_job_id":null,"html_url":"https://github.com/TRAILab/CaDDN","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TRAILab%2FCaDDN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TRAILab%2FCaDDN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TRAILab%2FCaDDN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TRAILab%2FCaDDN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TRAILab","download_url":"https://codeload.github.com/TRAILab/CaDDN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244660193,"owners_count":20489296,"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":"2024-07-31T03:02:05.621Z","updated_at":"2025-03-20T17:30:45.791Z","avatar_url":"https://github.com/TRAILab.png","language":"Python","funding_links":[],"categories":["Python","六、PV2BEV method summary"],"sub_categories":["1. Summary of PV2BEV based on depth method"],"readme":"\u003cimg src=\"docs/trailab.png\" align=\"right\" width=\"20%\"\u003e\n\n# CaDDN\n\n`CaDDN` is a monocular-based 3D object detection method. This repository is based off of [`[OpenPCDet]`](https://github.com/open-mmlab/OpenPCDet).\n\n**Categorical Depth Distribution Network for Monocular 3D Object Detection**\\\nCody Reading, Ali Harakeh, Julia Chae, and Steven L. Waslander\\\n**[[Paper](https://arxiv.org/abs/2103.01100)]**\n\n\n## Overview\n- [Changelog](#changelog)\n- [Model Zoo](#model-zoo)\n- [Installation](docs/INSTALL.md)\n- [Getting Started](docs/GETTING_STARTED.md)\n- [Citation](#citation)\n\n\n## Changelog\n[2021-03-16] `CaDDN` v0.3.0 is released.\n\n## Introduction\n\n\n### What does `CaDDN` do?\n\n`CaDDN` is a general PyTorch-based method for 3D object detection from monocular images.\nAt the time of submission, `CaDDN` achieved first 1st place among published monocular methods on the [Kitti 3D object detection benchmark](http://www.cvlibs.net/datasets/kitti/eval_object.php?obj_benchmark=3d). We welcome contributions to this project.\n\n### `CaDDN` design pattern\nWe inherit the design pattern from [`[OpenPCDet]`](https://github.com/open-mmlab/OpenPCDet).\n\n* Data-Model separation with unified point cloud coordinate for easily extending to custom datasets:\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/dataset_vs_model.png\" width=\"95%\" height=\"320\"\u003e\n\u003c/p\u003e\n\n* Unified 3D box definition: (x, y, z, dx, dy, dz, heading).\n\n## Model Zoo\n\n### KITTI 3D Object Detection Baselines\nSelected supported methods are shown in the below table. The results are the 3D detection performance of Car class on the *val* set of KITTI dataset.\n* All models are trained with 2 Tesla T4 GPUs and are available for download.\n* The training time is measured with 2 Tesla T4 GPUs and PyTorch 1.4.\n\n|                                             | training time | Easy@R40 | Moderate@R40 | Hard@R40  | download |\n|---------------------------------------------|----------:|:-------:|:-------:|:-------:|:---------:|\n| [CaDDN](tools/cfgs/kitti_models/CaDDN.yaml) |~76 hours| 23.77 | 16.07 | 13.61 | [model-774M](https://drive.google.com/file/d/13HGW3_zCTKHGVtr_JDHD4Wv64PP5Z2mG/view?usp=sharing) |\n\n## Installation\n\nPlease refer to [INSTALL.md](docs/INSTALL.md) for the installation of `CaDDN`.\n\n## Getting Started\n\nPlease refer to [GETTING_STARTED.md](docs/GETTING_STARTED.md) to learn more usage about this project.\n\n\n## License\n\n`CaDDN` is released under the [Apache 2.0 license](LICENSE).\n\n## Acknowledgement\n`CaDDN` is an open source project for monocular-based 3D scene perception.\nWe would like to thank the authors of [`OpenPCDet`](https://github.com/open-mmlab/OpenPCDet) for their open-source release of their 3D object detection codebase.\n\n\n## Citation\nIf you find this project useful in your research, please consider citing:\n```\n@article{CaDDN,\n    title={Categorical Depth DistributionNetwork for Monocular 3D Object Detection},\n    author={Cody Reading and\n            Ali Harakeh and\n            Julia Chae and\n            Steven L. Waslander},\n    journal = {CVPR},\n    year={2021}\n}\n```\n\n\n## Contribution\nWelcome to be a member of the CaDDN development team by contributing to this repo, and feel free to contact us for any potential contributions.\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTRAILab%2FCaDDN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FTRAILab%2FCaDDN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTRAILab%2FCaDDN/lists"}