mmhuman3d

OpenMMLab 3D Human Parametric Model Toolbox and Benchmark

https://github.com/open-mmlab/mmhuman3d

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Committers with academic emails
    3 of 35 committers (8.6%) from academic institutions
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (14.9%) to scientific vocabulary

Keywords from Contributors

vision-transformers human-parametric-model motion-capture smpl smpl-x animal-pose-estimation cpm crowdpose face-keypoint freihand
Last synced: 6 months ago · JSON representation ·

Repository

OpenMMLab 3D Human Parametric Model Toolbox and Benchmark

Basic Info
Statistics
  • Stars: 1,359
  • Watchers: 25
  • Forks: 149
  • Open Issues: 133
  • Releases: 9
Created over 4 years ago · Last pushed over 1 year ago
Metadata Files
Readme Contributing License Code of conduct Citation

README.md



[![Documentation](https://readthedocs.org/projects/mmhuman3d/badge/?version=latest)](https://mmhuman3d.readthedocs.io/en/latest/?badge=latest) [![actions](https://github.com/open-mmlab/mmhuman3d/workflows/build/badge.svg)](https://github.com/open-mmlab/mmhuman3d/actions) [![codecov](https://codecov.io/gh/open-mmlab/mmhuman3d/branch/main/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmhuman3d) [![PyPI](https://img.shields.io/pypi/v/mmhuman3d)](https://pypi.org/project/mmhuman3d/) [![LICENSE](https://img.shields.io/github/license/open-mmlab/mmhuman3d.svg)](https://github.com/open-mmlab/mmhuman3d/blob/main/LICENSE) [![Percentage of issues still open](https://isitmaintained.com/badge/open/open-mmlab/mmhuman3d.svg)](https://github.com/open-mmlab/mmhuman3d/issues)

Introduction

English | 简体中文

MMHuman3D is an open-source PyTorch-based codebase for the use of 3D human parametric models in computer vision and computer graphics. It is a part of the OpenMMLab project.

The main branch works with PyTorch 1.7+.

If you are interested in multi-view motion capture, please refer to XRMoCap for more details.

https://user-images.githubusercontent.com/62529255/144362861-e794b404-c48f-4ebe-b4de-b91c3fbbaa3b.mp4

Major Features

  • Reproducing popular methods with a modular framework

MMHuman3D reimplements popular methods, allowing users to reproduce SOTAs with one line of code. The modular framework is convenient for rapid prototyping: the users may attempt various hyperparameter settings and even network architectures, without actually modifying the code.

  • Supporting various datasets with a unified data convention

With the help of a convention toolbox, a unified data format HumanData is used to align all supported datasets. Preprocessed data files are also available.

  • Versatile visualization toolbox

A suite of differential visualization tools for human parametric model rendering (including part segmentation, depth map and point clouds) and conventional 2D/3D keypoints are available.

News

  • 2023-04-05: MMHuman3D v0.11.0 is released. Major updates include:
  • 2022-10-12: MMHuman3D v0.10.0 is released. Major updates include:
    • Add webcam demo and real-time renderer
    • Update dataloader to speed up training
    • Add balanced MSE loss for imbalanced HMR training
  • 2022-07-08: MMHuman3D v0.9.0 is released. Major updates include:
    • Support SMPL-X estimation with ExPose for simultaneous recovery of face, hands and body
    • Support new body model STAR
    • Release of GTA-Human dataset with SPIN-FT (51.98 mm) and PARE-FT (46.84 mm) baselines! (Official)
    • Refactor registration and improve performance of SPIN to 57.54 mm

Benchmark and Model Zoo

More details can be found in model_zoo.md.

Supported body models:

(click to collapse) - [x] [SMPL](https://smpl.is.tue.mpg.de/) (SIGGRAPH Asia'2015) - [x] [SMPL-X](https://smpl-x.is.tue.mpg.de/) (CVPR'2019) - [x] [MANO](https://mano.is.tue.mpg.de/) (SIGGRAPH ASIA'2017) - [x] [FLAME](https://flame.is.tue.mpg.de/) (SIGGRAPH ASIA'2017) - [x] [STAR](https://star.is.tue.mpg.de/) (ECCV'2020)

Supported methods:

(click to collapse) - [x] [SMPLify](https://smplify.is.tue.mpg.de/) (ECCV'2016) - [x] [SMPLify-X](https://smpl-x.is.tue.mpg.de/) (CVPR'2019) - [x] [HMR](https://akanazawa.github.io/hmr/) (CVPR'2018) - [x] [SPIN](https://www.seas.upenn.edu/~nkolot/projects/spin/) (ICCV'2019) - [x] [VIBE](https://github.com/mkocabas/VIBE) (CVPR'2020) - [x] [HybrIK](https://jeffli.site/HybrIK/) (CVPR'2021) - [x] [PARE](https://pare.is.tue.mpg.de/) (ICCV'2021) - [x] [DeciWatch](https://ailingzeng.site/deciwatch) (ECCV'2022) - [x] [SmoothNet](https://ailingzeng.site/smoothnet) (ECCV'2022) - [x] [ExPose](https://expose.is.tue.mpg.de) (ECCV'2020) - [x] [BalancedMSE](https://sites.google.com/view/balanced-mse/home) (CVPR'2022) - [x] [PyMAF-X](https://www.liuyebin.com/pymaf-x/) (arXiv'2022) - [x] [ExPose](configs/expose) (ECCV'2020) - [x] [PyMAF-X](configs/pymafx) (arXiv'2022) - [x] [CLIFF](configs/cliff) (ECCV'2022)

Supported datasets:

(click to collapse) - [x] [3DPW](https://virtualhumans.mpi-inf.mpg.de/3DPW/) (ECCV'2018) - [x] [AGORA](https://agora.is.tue.mpg.de/) (CVPR'2021) - [x] [AMASS](https://amass.is.tue.mpg.de/) (ICCV'2019) - [x] [COCO](https://cocodataset.org/#home) (ECCV'2014) - [x] [COCO-WholeBody](https://github.com/jin-s13/COCO-WholeBody) (ECCV'2020) - [x] [CrowdPose](https://github.com/Jeff-sjtu/CrowdPose) (CVPR'2019) - [x] [EFT](https://github.com/facebookresearch/eft) (3DV'2021) - [x] [GTA-Human](https://caizhongang.github.io/projects/GTA-Human/) (arXiv'2021) - [x] [Human3.6M](http://vision.imar.ro/human3.6m/description.php) (TPAMI'2014) - [x] [InstaVariety](https://github.com/akanazawa/human_dynamics/blob/master/doc/insta_variety.md) (CVPR'2019) - [x] [LSP](https://sam.johnson.io/research/lsp.html) (BMVC'2010) - [x] [LSP-Extended](https://sam.johnson.io/research/lspet.html) (CVPR'2011) - [x] [MPI-INF-3DHP](http://gvv.mpi-inf.mpg.de/3dhp-dataset/) (3DC'2017) - [x] [MPII](http://human-pose.mpi-inf.mpg.de/) (CVPR'2014) - [x] [Penn Action](http://dreamdragon.github.io/PennAction/) (ICCV'2012) - [x] [PoseTrack18](https://posetrack.net/users/download.php) (CVPR'2018) - [x] [SURREAL](https://www.di.ens.fr/willow/research/surreal/data/) (CVPR'2017) - [x] [UP3D](https://files.is.tuebingen.mpg.de/classner/up/) (CVPR'2017) - [x] [FreiHand](https://lmb.informatik.uni-freiburg.de/projects/freihand/) (ICCV'2019) - [x] [EHF](https://smpl-x.is.tue.mpg.de/) (CVPR'2019) - [x] [Stirling/ESRC-Face3D](http://pics.psych.stir.ac.uk/ESRC/index.htm) (FG'2018)

We will keep up with the latest progress of the community, and support more popular methods and frameworks.

If you have any feature requests, please feel free to leave a comment in the wishlist.

Get Started

Please see getting_started.md for the basic usage of MMHuman3D.

License

This project is released under the Apache 2.0 license. Some supported methods may carry additional licenses.

Citation

If you find this project useful in your research, please consider citing:

bibtex @misc{mmhuman3d, title={OpenMMLab 3D Human Parametric Model Toolbox and Benchmark}, author={MMHuman3D Contributors}, howpublished = {\url{https://github.com/open-mmlab/mmhuman3d}}, year={2021} }

Contributing

We appreciate all contributions to improve MMHuman3D. Please refer to CONTRIBUTING.md for the contributing guideline.

Acknowledgement

MMHuman3D is an open source project that is contributed by researchers and engineers from both the academia and the industry. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedback. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new models.

Projects in OpenMMLab

  • MMCV: OpenMMLab foundational library for computer vision.
  • MIM: MIM Installs OpenMMLab Packages.
  • MMClassification: OpenMMLab image classification toolbox and benchmark.
  • MMDetection: OpenMMLab detection toolbox and benchmark.
  • MMDetection3D: OpenMMLab next-generation platform for general 3D object detection.
  • MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
  • MMAction2: OpenMMLab next-generation action understanding toolbox and benchmark.
  • MMTracking: OpenMMLab video perception toolbox and benchmark.
  • MMPose: OpenMMLab pose estimation toolbox and benchmark.
  • MMEditing: OpenMMLab image and video editing toolbox.
  • MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding.
  • MMGeneration: OpenMMLab next-generation toolbox for generative models.
  • MMFlow: OpenMMLab optical flow toolbox and benchmark.
  • MMFewShot: OpenMMLab FewShot Learning Toolbox and Benchmark.
  • MMHuman3D: OpenMMLab 3D Human Parametric Model Toolbox and Benchmark.
  • MMSelfSup: OpenMMLab self-supervised learning toolbox and benchmark.
  • MMRazor: OpenMMLab model compression toolbox and benchmark.
  • MMDeploy: OpenMMLab model deployment framework.

Owner

  • Name: OpenMMLab
  • Login: open-mmlab
  • Kind: organization
  • Location: China

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - name: "MMHuman3D Contributors"
title: "MMHuman3D: OpenMMLab 3D Human Parametric Model Toolbox and Benchmark"
date-released: 2021-12-01
url: "https://github.com/open-mmlab/mmhuman3d"
license: Apache-2.0

GitHub Events

Total
  • Issues event: 4
  • Watch event: 143
  • Issue comment event: 1
  • Push event: 11
  • Fork event: 17
Last Year
  • Issues event: 4
  • Watch event: 143
  • Issue comment event: 1
  • Push event: 11
  • Fork event: 17

Committers

Last synced: 12 months ago

All Time
  • Total Commits: 245
  • Total Committers: 35
  • Avg Commits per committer: 7.0
  • Development Distribution Score (DDS): 0.841
Past Year
  • Commits: 3
  • Committers: 3
  • Avg Commits per committer: 1.0
  • Development Distribution Score (DDS): 0.667
Top Committers
Name Email Commits
LazyBusyYang g****n@o****m 39
Zhongang Cai 6****g 34
pangyyyyy p****6@g****m 33
Lei Yang y****v@g****m 32
ttxskk s****s@g****m 22
JasonBoy1 w****2@1****m 20
mingyuan-zhang z****8@g****m 15
Jacob_Liu s****u@s****h 6
jiaqiAA 6****A 5
LengYue l****e@l****e 3
Tyler Luan t****n@1****m 3
Wenjia Wang 3****1 3
Xuan Ju 8****7 3
Daxuan K****7@h****m 3
oneScotch 7****h 2
Zhu Shuai z****3@1****m 2
Shannon 7****s 2
rshaojimmy r****o@l****k 1
Haofan Wang h****i@g****m 1
zhengjie.xu j****e@g****m 1
wooil p****i@g****m 1
wendaizhou 5****u 1
liuzhe 5****1 1
innerlee 3****0@q****m 1
ailingzengzzz a****z@g****m 1
ZHELUN SHI 4****7 1
Yunfeng Wang v****a 1
Yongtao Ge y****e@a****u 1
Yining Li l****2@g****m 1
Yinghao Zhu y****9@g****m 1
and 5 more...
Committer Domains (Top 20 + Academic)

Issues and Pull Requests

Last synced: 7 months ago

All Time
  • Total issues: 102
  • Total pull requests: 61
  • Average time to close issues: about 1 month
  • Average time to close pull requests: about 1 month
  • Total issue authors: 73
  • Total pull request authors: 24
  • Average comments per issue: 1.67
  • Average comments per pull request: 1.43
  • Merged pull requests: 37
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 8
  • Pull requests: 1
  • Average time to close issues: 6 days
  • Average time to close pull requests: 2 days
  • Issue authors: 6
  • Pull request authors: 1
  • Average comments per issue: 0.25
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • lucasjinreal (8)
  • flyyyyer (5)
  • felixshing (4)
  • shihzenq (3)
  • SWWdz (3)
  • gjmm07 (3)
  • github1838 (2)
  • Dipankar1997161 (2)
  • luohao123 (2)
  • zhewei-mt (2)
  • Darius-H (2)
  • PMPBinZhang (2)
  • ChennyDeng (2)
  • WenjiaWang0312 (2)
  • yuchen-ji (2)
Pull Request Authors
  • caizhongang (8)
  • Wei-Chen-hub (6)
  • oneScotch (6)
  • ttxskk (6)
  • JacobLiu-S (6)
  • jiaqiAA (5)
  • pangyyyyy (3)
  • Zessay (2)
  • yhzhu99 (2)
  • WenjiaWang0312 (2)
  • crazysteeaam (2)
  • Naive-Bayes (2)
  • wendaizhou (1)
  • vra (1)
  • Fubuki901 (1)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 2
  • Total downloads:
    • pypi 182 last-month
  • Total dependent packages: 0
    (may contain duplicates)
  • Total dependent repositories: 1
    (may contain duplicates)
  • Total versions: 18
  • Total maintainers: 1
proxy.golang.org: github.com/open-mmlab/mmhuman3d
  • Versions: 9
  • Dependent Packages: 0
  • Dependent Repositories: 0
Rankings
Dependent packages count: 6.5%
Average: 6.7%
Dependent repos count: 6.9%
Last synced: 7 months ago
pypi.org: mmhuman3d

OpenMMLab 3D Human Parametric Model Toolbox and Benchmark

  • Versions: 9
  • Dependent Packages: 0
  • Dependent Repositories: 1
  • Downloads: 182 Last month
Rankings
Stargazers count: 2.0%
Forks count: 4.3%
Dependent packages count: 7.3%
Average: 12.0%
Dependent repos count: 22.2%
Downloads: 23.9%
Maintainers (1)
Last synced: 7 months ago

Dependencies

requirements/docs.txt pypi
  • docutils ==0.16.0
  • myst-parser *
  • sphinx ==4.0.2
  • sphinx-copybutton *
  • sphinx_markdown_tables *
  • sphinx_rtd_theme ==0.5.2
requirements/readthedocs.txt pypi
  • mmcv *
  • torch *
  • torchvision *
requirements/runtime.txt pypi
  • astropy *
  • cdflib <0.4.0
  • chumpy *
  • colormap *
  • easydev *
  • h5py *
  • matplotlib *
  • numpy *
  • opencv-python *
  • pandas *
  • pickle5 *
  • scikit-image *
  • scipy *
  • smplx *
  • tqdm *
  • vedo *
requirements/tests.txt pypi
  • codecov *
  • flake8 *
  • interrogate *
  • isort ==4.3.21
  • pytest *
  • xdoctest >=0.10.0
  • yapf *
.github/workflows/build.yml actions
  • actions/checkout v2 composite
  • codecov/codecov-action v2 composite
  • conda-incubator/setup-miniconda v2 composite
.github/workflows/lint.yml actions
  • actions/checkout v2 composite
  • actions/setup-python v2 composite
.github/workflows/publish-to-pypi.yml actions
  • actions/checkout v2 composite
  • actions/setup-python v1 composite
requirements.txt pypi
setup.py pypi