AI Rank
← Open Source
MVIG-SJTU

AlphaPose

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System.

ModelsVision modelsPython
Open on GitHub
Momentum
+-1stars in 24 hours-0.0%
8.61k
Stars
2.02k
Forks
+-1
This week
16
Contributors
Created 2018-01-17 · Updated 2026-10-16 · #18424 today
Top developers
Fang-HaoshuHaoyiZhujeffffffli

MVIG-SJTU/AlphaPose is ranked 18,424 with 8,609 stars.

Same-category comparison

MVIG-SJTU/AlphaPose is ranked 18,424 among these 8 peers; facebookresearch/DiT is ranked 18,423.

Same-category comparison
NameRankMetrics
databrickslabs/dolly18,403
Language:
Python
Stars:
10,805
Forks:
1,130
Description:
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform.
facebookresearch/maskrcnn-benchmark18,412
Language:
Python
Stars:
9,359
Forks:
2,450
Description:
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
facebookresearch/ImageBind18,418
Language:
Python
Stars:
9,075
Forks:
839
Description:
ImageBind One Embedding Space to Bind Them All.
facebookresearch/DiT18,423
Language:
Python
Stars:
8,675
Forks:
817
Description:
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers".
facebookresearch/mae18,433
Language:
Python
Stars:
8,361
Forks:
1,345
Description:
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377.
LianjiaTech/BELLE18,434
Language:
HTML
Stars:
8,265
Forks:
755
openai/jukebox18,439
Language:
Python
Stars:
8,029
Forks:
1,439
Description:
Code for the paper "Jukebox: A Generative Model for Music".
jaywalnut310/vits18,440
Language:
Python
Stars:
7,894
Forks:
1,378
Description:
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguagePython
CategoryModels
SubcategoryVision models
Stars8,609
Forks2,019
Contributors16
Created date2018-01-17
Updated date2026-10-16
Stars in 1 day-1
Stars in 7 days-1
Rank18,424
Previous rank7,277
Rank change-11,147
7-day stars rank16,645
Previous 7-day stars rank11,724
7-day stars rank change-4,921
Total stars rank1,672
Previous total stars rank1,668
Total stars rank change-4
CountryChina
README summary

Nov 2022: **AlphaPose paper** is released! Checkout the paper for more details about this project. Sep 2022: **Jittor** version of AlphaPose is released! 45x speed up with resnet50 backbone on the training stage. HybrIK for 3D pose and shape estimation is supported! Stronger whole body(face,hand,foot) keypoints! Include whole body(face,hand,foot) keypoints! Apr 2019: **MXNet** version of AlphaPose is released! It runs at **23 fps** on COCO validation set. Feb 2019: CrowdPose is integrated into AlphaPose

Now! Dec 2018: General version of PoseFlow is released! 3X Faster and support pose tracking results visualization! It runs at **20 fps** on COCO validation set (4. 6 people per image on average) and achieves 71 mAP! AlphaPose AlphaPose is an accurate multi-person pose estimator, which is the **first open-source system that achieves 70+ mAP (75 mAP) on COCO dataset and 80+ mAP (82. ** To match poses that correspond to the same person across frames, we also provide

an efficient online pose tracker called Pose Flow. It is the **first open-source online pose tracker that achieves both 60+ mAP (66. ** AlphaPose supports both Linux and **Windows! ** Results Pose Estimation Results on COCO test-dev 2015: | Method | AP @0. 1** | More results and models are available in the docs/MODEL_ZOO. Pose Tracking Please read trackers/README. Installation Please check out docs/INSTALL. md Model Zoo Please check out docs/MODEL_ZOO. md Quick Start **Colab**: We provide

a colab example for your quick start. **Inference**: Inference demo Inference SMPL (Download the SMPL model from here and put it in ). To enable tracking, please refer to this page. **Training**: Train from scratch **Validation**: Validate your model on MSCOCO val2017 Examples: Demo using model. More detailed inference options and examples, please refer to GETTING_STARTED. If it can not solve your problems or if you find any bugs, don't hesitate to comment on GitHub or make a pull request

! Contributors AlphaPose is based on RMPE(ICCV'17), authored by Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai and Cewu Lu, Cewu Lu is the corresponding author. Currently, it is maintained by Jiefeng Li\*, Hao-shu Fang\*, Haoyi Zhu, Yuliang Xiu and Chao Xu. The main contributors are listed in doc/contributors. py) We would really appreciate if you can offer any help and be the contributor of AlphaPose. Citation Please cite these papers in your publications if it helps

your research: If you used the 3D mesh reconstruction module, please also cite: If you used the PoseFlow tracking module, please also cite: License AlphaPose is freely available for free non-commercial use, and may be redistributed under these conditions. For commercial queries, please drop an e-mail at mvig. alphapose[at]gmail[dot]com and cc lucewu[[at]sjtu[dot]edu[dot]cn. We will send the detail agreement to you.

Frequently asked questions

How many stars and forks are recorded?

MVIG-SJTU/AlphaPose has 8,609 stars and 2,019 forks.

What is the repository rank?

MVIG-SJTU/AlphaPose is ranked 18,424.

What language and category are recorded?

MVIG-SJTU/AlphaPose has 8,609 stars, uses Python and belongs to Models.

Which repository is closest in rank?

MVIG-SJTU/AlphaPose is compared with facebookresearch/DiT, ranked 18,423 with 8,675 stars.

README
 ![](docs/logo.jpg)

News!

  • Nov 2022: AlphaPose paper is released! Checkout the paper for more details about this project.
  • Sep 2022: Jittor version of AlphaPose is released! It achieves 1.45x speed up with resnet50 backbone on the training stage.
  • July 2022: v0.6.0 version of AlphaPose is released! HybrIK for 3D pose and shape estimation is supported!
  • Jan 2022: v0.5.0 version of AlphaPose is released! Stronger whole body(face,hand,foot) keypoints! More models are availabel. Checkout docs/MODEL_ZOO.md
  • Aug 2020: v0.4.0 version of AlphaPose is released! Stronger tracking! Include whole body(face,hand,foot) keypoints! Colab now available.
  • Dec 2019: v0.3.0 version of AlphaPose is released! Smaller model, higher accuracy!
  • Apr 2019: MXNet version of AlphaPose is released! It runs at 23 fps on COCO validation set.
  • Feb 2019: CrowdPose is integrated into AlphaPose Now!
  • Dec 2018: General version of PoseFlow is released! 3X Faster and support pose tracking results visualization!
  • Sep 2018: v0.2.0 version of AlphaPose is released! It runs at 20 fps on COCO validation set (4.6 people per image on average) and achieves 71 mAP!

AlphaPose

AlphaPose is an accurate multi-person pose estimator, which is the first open-source system that achieves 70+ mAP (75 mAP) on COCO dataset and 80+ mAP (82.1 mAP) on MPII dataset. To match poses that correspond to the same person across frames, we also provide an efficient online pose tracker called Pose Flow. It is the first open-source online pose tracker that achieves both 60+ mAP (66.5 mAP) and 50+ MOTA (58.3 MOTA) on PoseTrack Challenge dataset.

AlphaPose supports both Linux and Windows!

 ![](docs/alphapose_17.gif)   

COCO 17 keypoints




 ![](docs/alphapose_26.gif)   

[Halpe 26 keypoints](https://github.com/Fang-Haoshu/Halpe-FullBody) + tracking




 ![](docs/alphapose_136.gif)   

[Halpe 136 keypoints](https://github.com/Fang-Haoshu/Halpe-FullBody) + tracking
[YouTube link](https://youtu.be/uze6chg-YeU)  





 ![](docs/alphapose_hybrik_smpl.gif)   

[SMPL](https://github.com/Jeff-sjtu/HybrIK) + tracking

Results

Pose Estimation

Results on COCO test-dev 2015:

Method AP @0.5:0.95 AP @0.5 AP @0.75 AP medium AP large
OpenPose (CMU-Pose) 61.8 84.9 67.5 57.1 68.2
Detectron (Mask R-CNN) 67.0 88.0 73.1 62.2 75.6
AlphaPose 73.3 89.2 79.1 69.0 78.6

Results on MPII full test set:

Method Head Shoulder Elbow Wrist Hip Knee Ankle Ave
OpenPose (CMU-Pose) 91.2 87.6 77.7 66.8 75.4 68.9 61.7 75.6
Newell & Deng 92.1 89.3 78.9 69.8 76.2 71.6 64.7 77.5
AlphaPose 91.3 90.5 84.0 76.4 80.3 79.9 72.4 82.1

More results and models are available in the docs/MODEL_ZOO.md.

Pose Tracking

 ![](docs/posetrack.gif) 
 ![](docs/posetrack2.gif)

Please read trackers/README.md for details.

CrowdPose

 ![](docs/crowdpose.gif)

Please read docs/CrowdPose.md for details.

Installation

Please check out docs/INSTALL.md

Model Zoo

Please check out docs/MODEL_ZOO.md

Quick Start

  • Colab: We provide a colab example for your quick start.

  • Inference: Inference demo

./scripts/inference.sh ${CONFIG} ${CHECKPOINT} ${VIDEO_NAME} # ${OUTPUT_DIR}, optional

Inference SMPL (Download the SMPL model basicModel_neutral_lbs_10_207_0_v1.0.0.pkl from here and put it in model_files/).

./scripts/inference_3d.sh ./configs/smpl/256x192_adam_lr1e-3-res34_smpl_24_3d_base_2x_mix.yaml ${CHECKPOINT} ${VIDEO_NAME} # ${OUTPUT_DIR}, optional

For high level API, please refer to ./scripts/demo_api.py. To enable tracking, please refer to this page.

  • Training: Train from scratch
./scripts/train.sh ${CONFIG} ${EXP_ID}
  • Validation: Validate your model on MSCOCO val2017
./scripts/validate.sh ${CONFIG} ${CHECKPOINT}

Examples:

Demo using FastPose model.

./scripts/inference.sh configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml pretrained_models/fast_res50_256x192.pth ${VIDEO_NAME}
#or
python scripts/demo_inference.py --cfg configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml --checkpoint pretrained_models/fast_res50_256x192.pth --indir examples/demo/
#or if you want to use yolox-x as the detector
python scripts/demo_inference.py --detector yolox-x --cfg configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml --checkpoint pretrained_models/fast_res50_256x192.pth --indir examples/demo/

Train FastPose on mscoco dataset.

./scripts/train.sh ./configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml exp_fastpose

More detailed inference options and examples, please refer to GETTING_STARTED.md

Common issue & FAQ

Check out faq.md for faq. If it can not solve your problems or if you find any bugs, don't hesitate to comment on GitHub or make a pull request!

Contributors

AlphaPose is based on RMPE(ICCV'17), authored by Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai and Cewu Lu, Cewu Lu is the corresponding author. Currently, it is maintained by Jiefeng Li*, Hao-shu Fang*, Haoyi Zhu, Yuliang Xiu and Chao Xu.

The main contributors are listed in doc/contributors.md.

TODO

  • [x] Multi-GPU/CPU inference
  • [x] 3D pose
  • [x] add tracking flag
  • [ ] PyTorch C++ version
  • [x] Add model trained on mixture dataset (Check the model zoo)
  • [ ] dense support
  • [x] small box easy filter
  • [x] Crowdpose support
  • [ ] Speed up PoseFlow
  • [x] Add stronger/light detectors (yolox is now supported)
  • [x] High level API (check the scripts/demo_api.py)

We would really appreciate if you can offer any help and be the contributor of AlphaPose.

Citation

Please cite these papers in your publications if it helps your research:

@article{alphapose,
  author = {Fang, Hao-Shu and Li, Jiefeng and Tang, Hongyang and Xu, Chao and Zhu, Haoyi and Xiu, Yuliang and Li, Yong-Lu and Lu, Cewu},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  title = {AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time},
  year = {2022}
}

@inproceedings{fang2017rmpe,
  title={{RMPE}: Regional Multi-person Pose Estimation},
  author={Fang, Hao-Shu and Xie, Shuqin and Tai, Yu-Wing and Lu, Cewu},
  booktitle={ICCV},
  year={2017}
}

@inproceedings{li2019crowdpose,
    title={Crowdpose: Efficient crowded scenes pose estimation and a new benchmark},
    author={Li, Jiefeng and Wang, Can and Zhu, Hao and Mao, Yihuan and Fang, Hao-Shu and Lu, Cewu},
    booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
    pages={10863--10872},
    year={2019}
}

If you used the 3D mesh reconstruction module, please also cite:

@inproceedings{li2021hybrik,
    title={Hybrik: A hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation},
    author={Li, Jiefeng and Xu, Chao and Chen, Zhicun and Bian, Siyuan and Yang, Lixin and Lu, Cewu},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={3383--3393},
    year={2021}
}

If you used the PoseFlow tracking module, please also cite:

@inproceedings{xiu2018poseflow,
  author = {Xiu, Yuliang and Li, Jiefeng and Wang, Haoyu and Fang, Yinghong and Lu, Cewu},
  title = {{Pose Flow}: Efficient Online Pose Tracking},
  booktitle={BMVC},
  year = {2018}
}

License

AlphaPose is freely available for free non-commercial use, and may be redistributed under these conditions. For commercial queries, please drop an e-mail at mvig.alphapose[at]gmail[dot]com and cc lucewu[[at]sjtu[dot]edu[dot]cn. We will send the detail agreement to you.

Nearby in the ranking
Similar items