{"id":19263754,"url":"https://github.com/calciferzh/minimal-body","last_synced_at":"2025-04-21T18:31:45.340Z","repository":{"id":80699257,"uuid":"429822682","full_name":"CalciferZh/minimal-body","owner":"CalciferZh","description":"A very simple baseline to estimate 2D \u0026 3D SMPL-compatible keypoints from a single color image.","archived":false,"fork":false,"pushed_at":"2021-11-20T11:18:04.000Z","size":297,"stargazers_count":56,"open_issues_count":0,"forks_count":5,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-04-01T15:11:53.718Z","etag":null,"topics":["3d-pose-estimation","computer-vision","deep-learning"],"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/CalciferZh.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":"2021-11-19T14:16:40.000Z","updated_at":"2025-01-14T09:39:18.000Z","dependencies_parsed_at":"2023-03-06T06:00:41.147Z","dependency_job_id":null,"html_url":"https://github.com/CalciferZh/minimal-body","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CalciferZh%2Fminimal-body","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CalciferZh%2Fminimal-body/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CalciferZh%2Fminimal-body/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CalciferZh%2Fminimal-body/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CalciferZh","download_url":"https://codeload.github.com/CalciferZh/minimal-body/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250111020,"owners_count":21376571,"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-pose-estimation","computer-vision","deep-learning"],"created_at":"2024-11-09T19:36:45.456Z","updated_at":"2025-04-21T18:31:45.335Z","avatar_url":"https://github.com/CalciferZh.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Minimal Body\n\n![teaser](teaser.png)\n\nA very simple baseline to estimate 2D \u0026 3D SMPL-compatible keypoints from a single color image.\n\nThe model file is only 51.2 MB and runs at 70fps on a 2080Ti.\n\n## Usage\n\n1. Download the pre-trained model [here](https://github.com/CalciferZh/minimal-body/releases/download/v1/minimal_body_v1.pth) into `model/`.\n2. Install the dependencies.\n3. Run `python example.py`.\n\nThe input image should already be cropped to a 4:3 portrait with the subject in the center.\n\n## Misc\n\nWe will __not__ release the training code.\n\nThe model is trained using the following datasets jointly:\n* [COCO](https://cocodataset.org/)\n* [MPII2D](http://human-pose.mpi-inf.mpg.de/)\n* [MPII3D](https://vcai.mpi-inf.mpg.de/3dhp-dataset/)\n* [HUMBI](https://humbi-data.net/)\n* [HM36M](http://vision.imar.ro/human3.6m/description.php)\n* [MTC](http://domedb.perception.cs.cmu.edu/mtc.html)\n* [SPIN](https://github.com/nkolot/SPIN)\n\nPlease also check the license of the listed datasets.\n\nIf you find it helpful, please consider citing our related paper:\n\n```\n@InProceedings{Zhou_2021_CVPR,\n    author    = {Zhou, Yuxiao and Habermann, Marc and Habibie, Ikhsanul and Tewari, Ayush and Theobalt, Christian and Xu, Feng},\n    title     = {Monocular Real-Time Full Body Capture With Inter-Part Correlations},\n    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},\n    month     = {June},\n    year      = {2021},\n    pages     = {4811-4822}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcalciferzh%2Fminimal-body","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcalciferzh%2Fminimal-body","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcalciferzh%2Fminimal-body/lists"}