{"id":15025856,"url":"https://github.com/una-dinosauria/3d-pose-baseline","last_synced_at":"2025-05-16T07:03:45.304Z","repository":{"id":41403610,"uuid":"88918009","full_name":"una-dinosauria/3d-pose-baseline","owner":"una-dinosauria","description":"A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.","archived":false,"fork":false,"pushed_at":"2020-09-26T02:27:50.000Z","size":327,"stargazers_count":1437,"open_issues_count":32,"forks_count":353,"subscribers_count":38,"default_branch":"master","last_synced_at":"2025-04-08T16:07:45.322Z","etag":null,"topics":["3d-vision","baseline","computer-vision","iccv-17","iccv-2017","tensorflow"],"latest_commit_sha":null,"homepage":"","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/una-dinosauria.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}},"created_at":"2017-04-20T23:05:16.000Z","updated_at":"2025-04-06T16:54:06.000Z","dependencies_parsed_at":"2022-07-13T09:50:29.069Z","dependency_job_id":null,"html_url":"https://github.com/una-dinosauria/3d-pose-baseline","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/una-dinosauria%2F3d-pose-baseline","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/una-dinosauria%2F3d-pose-baseline/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/una-dinosauria%2F3d-pose-baseline/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/una-dinosauria%2F3d-pose-baseline/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/una-dinosauria","download_url":"https://codeload.github.com/una-dinosauria/3d-pose-baseline/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254485052,"owners_count":22078767,"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-vision","baseline","computer-vision","iccv-17","iccv-2017","tensorflow"],"created_at":"2024-09-24T20:03:10.554Z","updated_at":"2025-05-16T07:03:45.262Z","avatar_url":"https://github.com/una-dinosauria.png","language":"Python","funding_links":[],"categories":["🎭 3D Human Pose Estimation","Pose Estimation"],"sub_categories":["📚 Monocular 3D Pose Methods","Implementations"],"readme":"## 3d-pose-baseline\n\nThis is the code for the paper\n\nJulieta Martinez, Rayat Hossain, Javier Romero, James J. Little.\n_A simple yet effective baseline for 3d human pose estimation._\nIn ICCV, 2017. https://arxiv.org/pdf/1705.03098.pdf.\n\nThe code in this repository was mostly written by\n[Julieta Martinez](https://github.com/una-dinosauria),\n[Rayat Hossain](https://github.com/rayat137) and\n[Javier Romero](https://github.com/libicocco).\n\nWe provide a strong baseline for 3d human pose estimation that also sheds light\non the challenges of current approaches. Our model is lightweight and we strive\nto make our code transparent, compact, and easy-to-understand.\n\n### Dependencies\n\n* Python ≥ 3.5\n* [cdflib](https://github.com/MAVENSDC/cdflib)\n* [tensorflow](https://www.tensorflow.org/) 1.0 or later\n\n### First of all\n1. Watch our video: https://youtu.be/Hmi3Pd9x1BE\n\n2. Clone this repository\n\n```bash\ngit clone https://github.com/una-dinosauria/3d-pose-baseline.git\ncd 3d-pose-baseline\nmkdir -p data/h36m/\n```\n\n3. Get the data\n\nGo to http://vision.imar.ro/human3.6m/, log in, and download the `D3 Positions` files for subjects `[1, 5, 6, 7, 8, 9, 11]`,\nand put them under the folder `data/h36m`. Your directory structure should look like this\n```bash\nsrc/\nREADME.md\nLICENCE\n...\ndata/\n  └── h36m/\n    ├── Poses_D3_Positions_S1.tgz\n    ├── Poses_D3_Positions_S11.tgz\n    ├── Poses_D3_Positions_S5.tgz\n    ├── Poses_D3_Positions_S6.tgz\n    ├── Poses_D3_Positions_S7.tgz\n    ├── Poses_D3_Positions_S8.tgz\n    └── Poses_D3_Positions_S9.tgz\n```\n\nNow, move to the data folder, and uncompress all the data\n\n```bash\ncd data/h36m/\nfor file in *.tgz; do tar -xvzf $file; done\n```\n\nFinally, download the `code-v1.2.zip` file, unzip it, and copy the `metadata.xml` file under `data/h36m/`\n\nNow, your data directory should look like this:\n\n```bash\ndata/\n  └── h36m/\n    ├── metadata.xml\n    ├── S1/\n    ├── S11/\n    ├── S5/\n    ├── S6/\n    ├── S7/\n    ├── S8/\n    └── S9/\n\n```\n\nThere is one little fix we need to run for the data to have consistent names:\n\n```bash\nmv h36m/S1/MyPoseFeatures/D3_Positions/TakingPhoto.cdf \\\n   h36m/S1/MyPoseFeatures/D3_Positions/Photo.cdf\n\nmv h36m/S1/MyPoseFeatures/D3_Positions/TakingPhoto\\ 1.cdf \\\n   h36m/S1/MyPoseFeatures/D3_Positions/Photo\\ 1.cdf\n\nmv h36m/S1/MyPoseFeatures/D3_Positions/WalkingDog.cdf \\\n   h36m/S1/MyPoseFeatures/D3_Positions/WalkDog.cdf\n\nmv h36m/S1/MyPoseFeatures/D3_Positions/WalkingDog\\ 1.cdf \\\n   h36m/S1/MyPoseFeatures/D3_Positions/WalkDog\\ 1.cdf\n```\n\nAnd you are done!\n\nPlease note that we are currently not supporting SH detections anymore, only training from GT 2d detections is possible now.\n\n### Quick demo\n\nFor a quick demo, you can train for one epoch and visualize the results. To train, run\n\n`python src/predict_3dpose.py --camera_frame --residual --batch_norm --dropout 0.5 --max_norm --evaluateActionWise --epochs 1`\n\nThis should take about \u003c5 minutes to complete on a GTX 1080, and give you around 56 mm of error on the test set.\n\nNow, to visualize the results, simply run\n\n`python src/predict_3dpose.py --camera_frame --residual --batch_norm --dropout 0.5 --max_norm --evaluateActionWise --epochs 1 --sample --load 24371`\n\nThis will produce a visualization similar to this:\n\n![Visualization example](/imgs/viz_example.png?raw=1)\n\n### Training\n\nTo train a model with clean 2d detections, run:\n\n\u003c!-- `python src/predict_3dpose.py --camera_frame --residual` --\u003e\n`python src/predict_3dpose.py --camera_frame --residual --batch_norm --dropout 0.5 --max_norm --evaluateActionWise`\n\nThis corresponds to Table 2, bottom row. `Ours (GT detections) (MA)`\n\n\u003c!--\nTo train on Stacked Hourglass detections, run\n\n`python src/predict_3dpose.py --camera_frame --residual --batch_norm --dropout 0.5 --max_norm --evaluateActionWise --use_sh`\n\nThis corresponds to Table 2, next-to-last row. `Ours (SH detections) (MA)`\n\nOn a GTX 1080 GPU, this takes \u003c8 ms for forward+backward computation, and\n\u003c6 ms for forward-only computation per batch of 64.\n--\u003e\n\n\u003c!--\n### Pre-trained model\n\nWe also provide a model pre-trained on ground truth 2d detections, available through [google drive](https://drive.google.com/file/d/0BxWzojlLp259MF9qSFpiVjl0cU0/view?usp=sharing).\n\nTo test the model, decompress the file at the top level of this project, and call\n\n`python src/predict_3dpose.py --camera_frame --residual --batch_norm --dropout 0.5 --max_norm --evaluateActionWise --epochs 200 --sample --load 4874200`\n--\u003e\n\n\u003c!--\n### Fine-tuned stacked-hourglass detections\n\nYou can find the detections produced by Stacked Hourglass after fine-tuning on the H3.6M dataset on [google drive](https://drive.google.com/open?id=0BxWzojlLp259S2FuUXJ6aUNxZkE).\n--\u003e\n\n### Citing\n\nIf you use our code, please cite our work\n\n```\n@inproceedings{martinez_2017_3dbaseline,\n  title={A simple yet effective baseline for 3d human pose estimation},\n  author={Martinez, Julieta and Hossain, Rayat and Romero, Javier and Little, James J.},\n  booktitle={ICCV},\n  year={2017}\n}\n```\n\n### Other implementations\n\n* [Pytorch](https://github.com/weigq/3d_pose_baseline_pytorch) by [@weigq](https://github.com/weigq)\n* [MXNet/Gluon](https://github.com/lck1201/simple-effective-3Dpose-baseline) by [@lck1201](https://github.com/lck1201)\n\n### Extensions\n\n* [@ArashHosseini](https://github.com/ArashHosseini) maintains [a fork](https://github.com/ArashHosseini/3d-pose-baseline) for estimating 3d human poses using the 2d poses estimated by either [OpenPose](https://github.com/ArashHosseini/openpose) or [tf-pose-estimation](https://github.com/ildoonet/tf-pose-estimation) as input.\n\n### License\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funa-dinosauria%2F3d-pose-baseline","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Funa-dinosauria%2F3d-pose-baseline","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funa-dinosauria%2F3d-pose-baseline/lists"}