{"id":20906077,"url":"https://github.com/arthur151/dynacam","last_synced_at":"2025-05-13T05:31:24.768Z","repository":{"id":170339367,"uuid":"606396942","full_name":"Arthur151/DynaCam","owner":"Arthur151","description":"[CVPR 2023] DynaCam dataset - 3D human trajectories in global coordinates from videos captured by dynamic cameras","archived":false,"fork":false,"pushed_at":"2023-06-30T13:10:26.000Z","size":22,"stargazers_count":79,"open_issues_count":4,"forks_count":3,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-04-01T18:50:14.658Z","etag":null,"topics":["3d-human","global-coordinates","trajectory"],"latest_commit_sha":null,"homepage":"http://www.yusun.work/TRACE/TRACE.html","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/Arthur151.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}},"created_at":"2023-02-25T11:16:03.000Z","updated_at":"2024-12-12T07:25:41.000Z","dependencies_parsed_at":null,"dependency_job_id":"27426689-c011-4197-b6ce-cddb6cec5756","html_url":"https://github.com/Arthur151/DynaCam","commit_stats":{"total_commits":11,"total_committers":1,"mean_commits":11.0,"dds":0.0,"last_synced_commit":"28f10785abda9240c2e64da56e27b6c74aaa35ac"},"previous_names":["arthur151/dynacam"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Arthur151%2FDynaCam","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Arthur151%2FDynaCam/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Arthur151%2FDynaCam/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Arthur151%2FDynaCam/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Arthur151","download_url":"https://codeload.github.com/Arthur151/DynaCam/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253883014,"owners_count":21978590,"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":["3d-human","global-coordinates","trajectory"],"created_at":"2024-11-18T13:28:53.086Z","updated_at":"2025-05-13T05:31:24.375Z","avatar_url":"https://github.com/Arthur151.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DynaCam\n| **[[Paper]](http://arxiv.org/abs/2306.02850)**  | **[[Video]](https://youtu.be/PX-7cuZuxJs)** | **[[Project Page]](http://www.yusun.work/TRACE/TRACE.html)** |\n\nDynaCam contains **in-the-wild** RGB videos captured by dynamic cameras, including annotations:  \n - **3D human trajectories in world coordinates**\n\nFor the details, please refer to our [project page](http://www.yusun.work/TRACE/TRACE.html).\n\n## Download\n\n[[Google drive]](https://drive.google.com/drive/folders/12zJYkTlKPn_3tlh96BQ6zuyEr3vTxqRw?usp=sharing) \n\n[[Baidu drive (百度网盘)]](https://pan.baidu.com/s/19Fi0o8LH2p2BamWnETqMDA?pwd=8zht) \n\nThe structure of dataset is supposed to be:\n```\n|-- DynaCam\n| --|-- video_frames\n|   |   |-- panorama_test\n|   |   |-- panorama_train\n|   |   |-- panorama_val\n|   |   |-- translation_test\n|   |   |-- translation_train\n|   |   |-- translation_val\n|   |-- annotations\n|   |   |-- *.npz\n```\n\n## Visualization\n\nTo visualize each video sequences and corresponding annotations, like 3D human trajectory, please download the [SMPL_NEUTRAL.pkl](https://github.com/Arthur151/DynaCam/releases/download/predictions/SMPL_NEUTRAL.pkl) and put it into 'assets/'\n, then run\n```\nsh install.sh\n# set the path to dynacam_folder in show_examples.py \npython show_examples.py \n```\n\u003cp float=\"center\"\u003e\n  \u003cimg src=\"https://github.com/Arthur151/DynaCam/releases/download/predictions/dynacam_vis_examples.gif\" width=\"50%\" /\u003e\n\u003c/p\u003e\n\u003c/p\u003e\nPress `stop` to stop the animation, draw the `slider` to sellect the frame, press `ESC` on your keyboard to go next. \n\n\n## Evaluation\nTo re-implement all results on DynaCam in our paper, please download [predictions](https://github.com/Arthur151/DynaCam/releases/tag/predictions), set the path in evaluation.py to ensure the structure like\n```\n|-- predictions\n| --|-- TRACE\n| --|-- GLAMR\n| --|-- bev_dpvo\n```\n, then run:\n```\nsh install.sh\npython evaluation.py\n```\n\n## Citation\nPlease cite our paper if you use DynaCam in your research. \n```bibtex\n@InProceedings{TRACE,\n    author = {Sun, Yu and Bao, Qian and Liu, Wu and Mei, Tao and Black, Michael J.},\n    title = {{TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments}}, \n    booktitle = {IEEE/CVF Conf.~on Computer Vision and Pattern Recognition (CVPR)}, \n    month = June, \n    year = {2023}}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farthur151%2Fdynacam","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farthur151%2Fdynacam","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farthur151%2Fdynacam/lists"}