If you find our works useful in your reasearch, please consider citing:

@article{li2018crowdpose,
  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},
  journal={arXiv preprint arXiv:1812.00324},
  year={2018}
}

This is the official repo of CVPR2019 paper CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark. Our proposed method surpasses the state-of-the-art methods on CrowdPose dataset by 5 mAP and results on MSCOCO dataset demonstrate the generalization ability of our method (comparatively 0.8 mAP higher). Images in our proposed CrowdPose dataset have a uniform distribution of Crowd Index among [0, 1].

We provide evaluation tools for CrowdPose dataset. Our evaluation tools is developed based on @cocodataset/cocoapi. The source code of our model has been integrated into AlphaPose.

Train + Validation + Test Images (Google Drive)

Annotations (Google Drive)

Results on CrowdPose Validation:

Compare with state-of-the-art methods

Compare with open-source systems

Results on MSCOCO Validation:

CrowdPose is authored by Jiefeng Li, Can Wang, Hao Zhu, Yihuan Mao, Hao-Shu Fang, and Cewu Lu.