{ "info": { "author": "Vassilis Choutas", "author_email": "vassilis.choutas@tuebingen.mpg.de", "bugtrack_url": null, "classifiers": [], "description": "\n## SMPL-X: A new joint 3D model of the human body, face and hands together\n\n[[Paper Page](https://smpl-x.is.tue.mpg.de)] [[Paper](https://ps.is.tuebingen.mpg.de/uploads_file/attachment/attachment/497/SMPL-X.pdf)]\n[[Supp. Mat.](https://ps.is.tuebingen.mpg.de/uploads_file/attachment/attachment/498/SMPL-X-supp.pdf)]\n\n![SMPL-X Examples](./images/teaser_fig.png)\n\n## Table of Contents\n * [License](#license)\n * [Description](#description)\n * [Installation](#installation)\n * [Downloading the model](#downloading-the-model)\n * [Loading SMPL-X, SMPL+H and SMPL](#loading-smpl-x-smplh-and-smpl) \n * [SMPL and SMPL+H setup](#smpl-and-smplh-setup)\n * [Model loading](https://github.com/vchoutas/smplx#model-loading)\n * [Example](#example)\n * [Citation](#citation)\n * [Acknowledgments](#acknowledgments)\n * [Contact](#contact)\n\n## License\n\nSoftware Copyright License for **non-commercial scientific research purposes**.\nPlease read carefully the [terms and conditions](https://github.com/vchoutas/smplx/blob/master/LICENSE) and any accompanying documentation before you download and/or use the SMPL-X/SMPLify-X model, data and software, (the \"Model & Software\"), including 3D meshes, blend weights, blend shapes, textures, software, scripts, and animations. By downloading and/or using the Model & Software (including downloading, cloning, installing, and any other use of this github repository), you acknowledge that you have read these terms and conditions, understand them, and agree to be bound by them. If you do not agree with these terms and conditions, you must not download and/or use the Model & Software. Any infringement of the terms of this agreement will automatically terminate your rights under this [License](./LICENSE).\n\n## Disclaimer\n\nThe original images used for the figures 1 and 2 of the paper can be found in this link. \nThe images in the paper are used under license from gettyimages.com.\nWe have acquired the right to use them in the publication, but redistribution is not allowed.\nPlease follow the instructions on the given link to acquire right of usage.\nOur results are obtained on the 483 \u00d7 724 pixels resolution of the original images.\n\n## Description\n\n*SMPL-X* (SMPL eXpressive) is a unified body model with shape parameters trained jointly for the\nface, hands and body. *SMPL-X* uses standard vertex based linear blend skinning with learned corrective blend\nshapes, has N = 10, 475 vertices and K = 54 joints,\nwhich include joints for the neck, jaw, eyeballs and fingers. \nSMPL-X is defined by a function M(\u03b8, \u03b2, \u03c8), where \u03b8 is the pose parameters, \u03b2 the shape parameters and\n\u03c8 the facial expression parameters.\n\n\n## Installation\n\nTo install the model please follow the next steps in the specified order:\n1. To install from PyPi simply run: \n ```Shell\n pip install smplx[all]\n ```\n2. Clone this repository and install it using the *setup.py* script: \n```Shell\ngit clone https://github.com/vchoutas/smplx\npython setup.py install\n```\n\n## Downloading the model\n\nTo download the *SMPL-X* model go to [this project website](https://smpl-x.is.tue.mpg.de) and register to get access to the downloads section. \n\nTo download the *SMPL+H* model go to [this project website](http://mano.is.tue.mpg.de) and register to get access to the downloads section. \n\nTo download the *SMPL* model go to [this](http://smpl.is.tue.mpg.de) (male and female models) and [this](http://smplify.is.tue.mpg.de) (gender neutral model) project website and register to get access to the downloads section. \n\n## Loading SMPL-X, SMPL+H and SMPL\n\n### SMPL and SMPL+H setup\n\nThe loader gives the option to use any of the SMPL-X, SMPL+H and SMPL models. Depending on the model you want to use, please follow the respective download instructions. To switch between SMPL, SMPL+H and SMPL-X just change the *model_path* or *model_type* parameters. For more details please check the docs of the model classes.\nBefore using SMPL and SMPL+H you should follow the instructions in [tools/README.md](./tools/README.md) to remove the\nChumpy objects from both model pkls, as well as merge the MANO parameters with SMPL+H.\n\n### Model loading \n\nYou can either use the [create](https://github.com/vchoutas/smplx/blob/c63c02b478c5c6f696491ed9167e3af6b08d89b1/smplx/body_models.py#L54)\nfunction from [body_models](./smplx/body_models.py) or directly call the constructor for the \n[SMPL](https://github.com/vchoutas/smplx/blob/c63c02b478c5c6f696491ed9167e3af6b08d89b1/smplx/body_models.py#L106), \n[SMPL+H](https://github.com/vchoutas/smplx/blob/c63c02b478c5c6f696491ed9167e3af6b08d89b1/smplx/body_models.py#L395) and \n[SMPL-X](https://github.com/vchoutas/smplx/blob/c63c02b478c5c6f696491ed9167e3af6b08d89b1/smplx/body_models.py#L628) model. The path to the model can either be the path to the file with the parameters or a directory with the following structure:\n```bash\nmodels\n\u251c\u2500\u2500 smpl\n\u2502\u00a0\u00a0 \u251c\u2500\u2500 SMPL_FEMALE.pkl\n\u2502\u00a0\u00a0 \u2514\u2500\u2500 SMPL_MALE.pkl\n\u2502\u00a0\u00a0 \u2514\u2500\u2500 SMPL_NEUTRAL.pkl\n\u251c\u2500\u2500 smplh\n\u2502\u00a0\u00a0 \u251c\u2500\u2500 SMPLH_FEMALE.pkl\n\u2502\u00a0\u00a0 \u2514\u2500\u2500 SMPLH_MALE.pkl\n\u2514\u2500\u2500 smplx\n \u251c\u2500\u2500 SMPLX_FEMALE.npz\n \u251c\u2500\u2500 SMPLX_FEMALE.pkl\n \u251c\u2500\u2500 SMPLX_MALE.npz\n \u251c\u2500\u2500 SMPLX_MALE.pkl\n \u251c\u2500\u2500 SMPLX_NEUTRAL.npz\n \u2514\u2500\u2500 SMPLX_NEUTRAL.pkl\n```\n\n## Example\n\nAfter installing the *smplx* package and downloading the model parameters you should be able to run the *demo.py*\nscript to visualize the results. For this step you have to install the [pyrender](https://pyrender.readthedocs.io/en/latest/index.html) and [trimesh](https://trimsh.org/) packages.\n\n`python examples/demo.py --model-folder $SMPLX_FOLDER --plot-joints=True --gender=\"neutral\"`\n\n![SMPL-X Examples](./images/example.png)\n\n## Citation\n\nDepending on which model is loaded for your project, i.e. SMPL-X or SMPL+H or SMPL, please cite the most relevant work below, listed in the same order:\n\n```\n@inproceedings{SMPL-X:2019,\n title = {Expressive Body Capture: 3D Hands, Face, and Body from a Single Image},\n author = {Pavlakos, Georgios and Choutas, Vasileios and Ghorbani, Nima and Bolkart, Timo and Osman, Ahmed A. A. and Tzionas, Dimitrios and Black, Michael J.},\n booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},\n year = {2019}\n}\n```\n\n```\n@article{MANO:SIGGRAPHASIA:2017,\n title = {Embodied Hands: Modeling and Capturing Hands and Bodies Together},\n author = {Romero, Javier and Tzionas, Dimitrios and Black, Michael J.},\n journal = {ACM Transactions on Graphics, (Proc. SIGGRAPH Asia)},\n volume = {36},\n number = {6},\n series = {245:1--245:17},\n month = nov,\n year = {2017},\n month_numeric = {11}\n }\n```\n\n```\n@article{SMPL:2015,\n author = {Loper, Matthew and Mahmood, Naureen and Romero, Javier and Pons-Moll, Gerard and Black, Michael J.},\n title = {{SMPL}: A Skinned Multi-Person Linear Model},\n journal = {ACM Transactions on Graphics, (Proc. SIGGRAPH Asia)},\n month = oct,\n number = {6},\n pages = {248:1--248:16},\n publisher = {ACM},\n volume = {34},\n year = {2015}\n}\n```\n\nThis repository was originally developed for SMPL-X / SMPLify-X (CVPR 2019), you might be interested in having a look: [https://smpl-x.is.tue.mpg.de](https://smpl-x.is.tue.mpg.de).\n\n## Acknowledgments\n\n### Facial Contour\n\nSpecial thanks to [Soubhik Sanyal](https://github.com/soubhiksanyal) for sharing the Tensorflow code used for the facial\nlandmarks.\n\n## Contact\nThe code of this repository was implemented by [Vassilis Choutas](vassilis.choutas@tuebingen.mpg.de).\n\nFor questions, please contact [smplx@tue.mpg.de](smplx@tue.mpg.de).\n\nFor commercial licensing (and all related questions for business applications), please contact [ps-licensing@tue.mpg.de](ps-licensing@tue.mpg.de).\n\n\n", "description_content_type": "text/markdown", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "http://smpl-x.is.tuebingen.mpg.de", "keywords": "", "license": "", "maintainer": "", "maintainer_email": "", "name": "smplx", "package_url": "https://pypi.org/project/smplx/", "platform": "", "project_url": "https://pypi.org/project/smplx/", "project_urls": { "Homepage": "http://smpl-x.is.tuebingen.mpg.de" }, "release_url": "https://pypi.org/project/smplx/0.1.13/", "requires_dist": [ "numpy (>=1.16.2)", "torch (>=1.0.1.post2)", "torchgeometry (>=0.1.2)", "pyrender (>=0.1.23) ; extra == 'all'", "trimesh (>=2.37.6) ; extra == 'all'", "shapely ; extra == 'all'", "matplotlib ; extra == 'all'", "open3d-python ; extra == 'all'", "matplotlib ; extra == 'matplotlib'", "open3d-python ; extra == 'open3d'", "pyrender (>=0.1.23) ; extra == 'pyrender'", "trimesh (>=2.37.6) ; extra == 'pyrender'", "shapely ; extra == 'pyrender'" ], "requires_python": ">=3.6.0", "summary": "PyTorch module for loading the SMPLX body model", "version": "0.1.13" }, "last_serial": 5891674, "releases": { "0.1.10": [ { "comment_text": "", "digests": { "md5": "70bcf29e829d926e345bf811fe294eca", "sha256": "c349923a1cee2af42edebe819caf1abc402f8175f06d335dc3d79ac2c26093bb" }, "downloads": -1, "filename": "smplx-0.1.10-py3-none-any.whl", "has_sig": false, "md5_digest": "70bcf29e829d926e345bf811fe294eca", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.6.0", "size": 24893, "upload_time": "2019-06-12T16:26:44", "url": "https://files.pythonhosted.org/packages/a1/8b/726517c9937d65ec29d08a4c9c6964f54e23cd519e5479812a3b9bc922d0/smplx-0.1.10-py3-none-any.whl" } ], "0.1.11": [ { "comment_text": "", "digests": { "md5": "cb3e4bf77bf68cf3aa47fc2a3559e089", "sha256": "ec5a4979ced5c294db44f6c9181a921e4df0725ae4940d852b582118600f17a8" }, "downloads": -1, "filename": "smplx-0.1.11-py3-none-any.whl", "has_sig": false, "md5_digest": "cb3e4bf77bf68cf3aa47fc2a3559e089", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.6.0", "size": 24942, "upload_time": "2019-06-13T14:53:48", "url": "https://files.pythonhosted.org/packages/b5/63/ec1fdeace8629a56f80debcd5cb0561c4a26daa2309c6a6009e16506cc5a/smplx-0.1.11-py3-none-any.whl" } ], "0.1.12": [ { "comment_text": "", "digests": { "md5": "fd06972c732ec8b3441a7d520538d2bc", "sha256": "a6059b8e90d170f878f8fb944aa13b3bc8a53edbad0953e9f5185a49b96c4033" }, "downloads": -1, "filename": "smplx-0.1.12-py3-none-any.whl", "has_sig": false, "md5_digest": "fd06972c732ec8b3441a7d520538d2bc", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.6.0", "size": 24972, "upload_time": "2019-08-12T10:01:44", "url": "https://files.pythonhosted.org/packages/9f/93/6e98e0d304dcaf739d623da32f0cdbb714745bfd14a0c8592ba1744f9c5c/smplx-0.1.12-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "88cd80e38ab570fa5b44ad38b43a5440", "sha256": "bb4c20cdfc88e73cc51af771c6181ff04db5a5e900d006cc93dbf49d251b79a3" }, "downloads": -1, "filename": "smplx-0.1.12.tar.gz", "has_sig": false, "md5_digest": "88cd80e38ab570fa5b44ad38b43a5440", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.6.0", "size": 20183, "upload_time": "2019-08-12T10:01:46", "url": "https://files.pythonhosted.org/packages/24/9e/19a96fa92d58920121c728992fe6c4c7533a5830cd41bcd5a405a11e2d7f/smplx-0.1.12.tar.gz" } ], "0.1.13": [ { "comment_text": "", "digests": { "md5": "fca3cda665ba1d3c53981a037074de84", "sha256": "adbe0b3c4d3a062abeeeaa50e7e94d2a1591329580f144f36ada0086ef1fde72" }, "downloads": -1, "filename": "smplx-0.1.13-py3-none-any.whl", "has_sig": false, "md5_digest": "fca3cda665ba1d3c53981a037074de84", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.6.0", "size": 26209, "upload_time": "2019-09-26T17:04:55", "url": "https://files.pythonhosted.org/packages/6a/2e/0b17c1850ede05d4fc482e5f3feb6e7227abd4a527af233fcf94df4bbb80/smplx-0.1.13-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "60c79ba096fff876afba5c5f572b8351", "sha256": "5cc796d057032c573095291ceca25b607a525fa3554204dfcf4aa0bbe46c65c1" }, "downloads": -1, "filename": "smplx-0.1.13.tar.gz", "has_sig": false, "md5_digest": "60c79ba096fff876afba5c5f572b8351", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.6.0", "size": 21327, "upload_time": "2019-09-26T17:04:57", "url": "https://files.pythonhosted.org/packages/15/00/812a6c62ad19cc6396240253b6ee81987d17decf82141f7d030f83c30697/smplx-0.1.13.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "fca3cda665ba1d3c53981a037074de84", "sha256": "adbe0b3c4d3a062abeeeaa50e7e94d2a1591329580f144f36ada0086ef1fde72" }, "downloads": -1, "filename": "smplx-0.1.13-py3-none-any.whl", "has_sig": false, "md5_digest": "fca3cda665ba1d3c53981a037074de84", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": ">=3.6.0", "size": 26209, "upload_time": "2019-09-26T17:04:55", "url": "https://files.pythonhosted.org/packages/6a/2e/0b17c1850ede05d4fc482e5f3feb6e7227abd4a527af233fcf94df4bbb80/smplx-0.1.13-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "60c79ba096fff876afba5c5f572b8351", "sha256": "5cc796d057032c573095291ceca25b607a525fa3554204dfcf4aa0bbe46c65c1" }, "downloads": -1, "filename": "smplx-0.1.13.tar.gz", "has_sig": false, "md5_digest": "60c79ba096fff876afba5c5f572b8351", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.6.0", "size": 21327, "upload_time": "2019-09-26T17:04:57", "url": "https://files.pythonhosted.org/packages/15/00/812a6c62ad19cc6396240253b6ee81987d17decf82141f7d030f83c30697/smplx-0.1.13.tar.gz" } ] }