{"id":14961281,"url":"https://github.com/nghorbani/amass","last_synced_at":"2025-04-12T21:28:54.865Z","repository":{"id":35461566,"uuid":"201422255","full_name":"nghorbani/amass","owner":"nghorbani","description":"Data preparation and loader for AMASS","archived":false,"fork":false,"pushed_at":"2024-07-25T11:10:05.000Z","size":8448,"stargazers_count":746,"open_issues_count":39,"forks_count":91,"subscribers_count":11,"default_branch":"master","last_synced_at":"2025-04-04T01:08:57.731Z","etag":null,"topics":["action-recognition","human","motion","motion-capture","pose-estimation"],"latest_commit_sha":null,"homepage":"https://amass.is.tue.mpg.de/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/nghorbani.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":"support_data/github_data/amass_sample.npz","governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-08-09T08:09:01.000Z","updated_at":"2025-04-02T06:23:17.000Z","dependencies_parsed_at":"2024-09-29T06:19:14.892Z","dependency_job_id":null,"html_url":"https://github.com/nghorbani/amass","commit_stats":{"total_commits":36,"total_committers":3,"mean_commits":12.0,"dds":0.5277777777777778,"last_synced_commit":"a9888a92a4e62533454aa43e5f979d9a8bc8c893"},"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nghorbani%2Famass","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nghorbani%2Famass/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nghorbani%2Famass/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nghorbani%2Famass/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nghorbani","download_url":"https://codeload.github.com/nghorbani/amass/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248634062,"owners_count":21136970,"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":["action-recognition","human","motion","motion-capture","pose-estimation"],"created_at":"2024-09-24T13:24:22.102Z","updated_at":"2025-04-12T21:28:54.844Z","avatar_url":"https://github.com/nghorbani.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AMASS: Archive of Motion Capture as Surface Shapes\n\n![alt text](support_data/github_data/datasets_preview.png \"Samples of bodies in AMASS recovered from Motion Capture sequences\")\n\n[AMASS](http://amass.is.tue.mpg.de) is a large database of human motion unifying different optical marker-based motion capture datasets by representing them within a common framework and parameterization. \n AMASS is readily useful for animation, visualization, and generating training data for deep learning.\n\nHere we provide tools and tutorials to use AMASS in your research projects. More specifically:\n- Following the recommended splits of data by AMASS, we provide three non-overlapping train/validation/test splits.\n- AMASS uses an extended version of [SMPL+H](http://mano.is.tue.mpg.de/) with [DMPLs](https://smpl.is.tue.mpg.de/). \nHere we show how to load different components and visualize a body model with AMASS data.\n- AMASS is also compatible with [SMPL](http://smpl.is.tue.mpg.de) and [SMPL-X](https://smpl-x.is.tue.mpg.de/) body models. \nWe show how to use the body data from AMASS to animate these models.\n## Table of Contents\n  * [Installation](#installation)\n  * [Body Models](#body-models)\n  * [Tutorials](#tutorials)\n  * [Citation](#citation)\n  * [License](#license)\n  * [Contact](#contact)\n\n## Installation\n**Requirements**\n- Python 3.7\n- [PyTorch 1.7.1](https://pytorch.org/get-started)\n- [Human Body Prior](https://github.com/nghorbani/human_body_prior)\n- [Pyrender](https://pyrender.readthedocs.io/en/latest/install/index.html#osmesa) for visualizations\n\nClone this repo and run the following from the root folder:\n```bash\npython install -r requirements.txt\npython setup.py develop\n```\n\n## Body Models\nAMASS uses [MoSh++](https://amass.is.tue.mpg.de) pipeline to fit [SMPL+H body model](https://mano.is.tue.mpg.de/)\nto human optical marker based motion capture (mocap) data.\nIn the paper we use SMPL+H with extended shape space, i.e. 16 betas, and 8 [DMPLs](https://smpl.is.tue.mpg.de/). \nPlease download models and place them them in body_models folder of this repository after you obtained the code from GitHub.\n\n## Tutorials\nWe release tools and Jupyter notebooks to demonstrate how to use AMASS to animate SMPL+H body model.\n\nFurthermore, as promised in the supplementary material of the paper, we release code to produce synthetic mocap using \n[DFaust](http://dfaust.is.tue.mpg.de) registrations.\n\nPlease refer to [tutorials](/notebooks) for further details.\n\n## Citation\nPlease cite the following paper if you use this code directly or indirectly in your research/projects:\n```\n@inproceedings{AMASS:2019,\n  title={AMASS: Archive of Motion Capture as Surface Shapes},\n  author={Mahmood, Naureen and Ghorbani, Nima and F. Troje, Nikolaus and Pons-Moll, Gerard and Black, Michael J.},\n  booktitle = {The IEEE International Conference on Computer Vision (ICCV)},\n  year={2019},\n  month = {Oct},\n  url = {https://amass.is.tue.mpg.de},\n  month_numeric = {10}\n}\n```\n## License\n\nSoftware Copyright License for **non-commercial scientific research purposes**.\nPlease read carefully the [terms and conditions](./LICENSE) \nand any accompanying documentation before you download and/or use the AMASS dataset, and software, (the \"Model \u0026 Software\"). \n By downloading and/or using the Model \u0026 Software \n (including downloading, cloning, installing, and any other use of this GitHub repository), \n you acknowledge that you have read these terms and conditions, understand them, \n and agree to be bound by them. If you do not agree with these terms and conditions, \n you must not download and/or use the Model \u0026 Software.\n  Any infringement of the terms of this agreement will automatically terminate your rights under this [License](./LICENSE).\n \n ## Contact\nThe code in this repository is developed by [Nima Ghorbani](https://nghorbani.github.io/).\n\nIf you have any questions you can contact us at [amass@tuebingen.mpg.de](mailto:amass@tuebingen.mpg.de).\n\nFor commercial licensing, please contact [ps-licensing@tue.mpg.de](mailto:ps-licensing@tue.mpg.de)\n\nTo find out about the latest developments stay tuned to [AMASS twitter](https://twitter.com/mocap_amass).\n\n## Contribute to AMASS\nThe research community needs more human motion data. \nIf you have interesting marker based motion capture data, and you are willing to share it for research purposes, \nthen we will label and clean your mocap and MoSh it for you and add it to the AMASS dataset, \nnaturally citing you as the original owner of the marker data.\nFor this purposes feel free to contact [amass@tuebingen.mpg.de](mailto:amass@tuebingen.mpg.de).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnghorbani%2Famass","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnghorbani%2Famass","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnghorbani%2Famass/lists"}