This is the official repo for ECCV2020 paper "Whole-Body Human Pose Estimation in the Wild". The slides of this work can be found in Slides. The repo contains COCO-WholeBody annotations proposed in this paper. Note that in our ECCV paper, all experiments are conducted on COCO-WholeBody V0.5. We further improve the annotation of the proposed dataset from V0.5 to V1.0. The benchmark results for COCO-WholeBody V1.0 can be found in MMPose. More introduction of COCO-WholeBody V1.0 is summarized in our recent TPAMI paper.
[2022.08.08] Our recent paper "ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild" has been published in IEEE Transactions on Pattern Analysis and Machine Intelligence. In this paper, we propose a neural architecture search framework, termed ZoomNAS, to promote both the accuracy and efficiency of whole-body pose estimation.
[2020.10.08] We put a fancy demo video to YouTube. The demo video is generated by MMPose. Enjoy :)
[2020.09.19] We have supported COCO-WholeBody in MMPose. A much stronger baseline model dark_pose_hrnet_w48+ with WholeBody AP 66.1% is provided for research purpose.
[2020.09.15] The evaluation tool is integrated into Extended COCO API for version>=1.5
COCO-WholeBody dataset is the first large-scale benchmark for whole-body pose estimation. It is an extension of COCO 2017 dataset with the same train/val split as COCO.
Here is an example of one annotated image.

For each person, we annotate 4 types of bounding boxes (person box, face box, left-hand box, and right-hand box) and 133 keypoints (17 for body, 6 for feet, 68 for face and 42 for hands). The face/hand box is defined as the minimal bounding rectangle of the keypoints. The keypoint annotations are illustrated as follows.
We provide evaluation tools for COCO-WholeBody dataset. Our evaluation tools is developed based on @cocodataset/cocoapi.
We also provide an example groundtruth file (example_gt.json) and an example pred file (example_pred.json).
python evaluation/evaluation_wholebody.py --gt_file evaluation/example_gt.json --res_file evaluation/example_pred.json
Compare with other popular datasets.
Overview of some popular public datasets for 2D keypoint estimation in RGB images. Kpt stands for keypoints, and #Kpt means the annotated number. ``Wild'' denotes whether the dataset is collected in-the-wild. * means head box.
Whole-body pose estimation results on our WholeBody benchmark.
WholeBody-Face (WBF) & WholeBody-Hand (WBH) are subsets of COCO-WholeBody.
We build WBF & WBH by extracting cropped face & hand images and annotations from COCO-WholeBody.
If you use this dataset in your project, please cite this paper.
@inproceedings{jin2020whole,
title={Whole-Body Human Pose Estimation in the Wild},
author={Jin, Sheng and Xu, Lumin and Xu, Jin and Wang, Can and Liu, Wentao and Qian, Chen and Ouyang, Wanli and Luo, Ping},
booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
year={2020}
}
@article{xu2022zoomnas,
title={ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild},
author={Xu, Lumin and Jin, Sheng and Liu, Wentao and Qian, Chen and Ouyang, Wanli and Luo, Ping and Wang, Xiaogang},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2022},
publisher={IEEE}
}
[1] Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2d human pose estimation: New benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)
[2] Duan, H., Lin, K.Y., Jin, S., Liu, W., Qian, C., Ouyang, W.: Trb: A novel triplet representation for understanding 2d human body. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 9479–9488 (2019)
[3] Li, J., Wang, C., Zhu, H., Mao, Y., Fang, H.S., Lu, C.: Crowdpose: Efficient crowded scenes pose estimation and a new benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 10863–10872 (2019)
[4] Andriluka, M., Iqbal, U., Insafutdinov, E., Pishchulin, L., Milan, A., Gall, J., Schiele, B.: Posetrack: A benchmark for human pose estimation and tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
[5] Wu, J., Zheng, H., Zhao, B., Li, Y., Yan, B., Liang, R., Wang, W., Zhou, S., Lin, G., Fu, Y., et al.: Ai challenger: a large-scale dataset for going deeper in image understanding. arXiv preprint arXiv:1711.06475 (2017)
[6] Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dolla ́r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: Proceedings of the European Conference on Computer Vision (ECCV) (2014)
[7] Wang, Y., Peng, C., Liu, Y.: Mask-pose cascaded cnn for 2d hand pose estimation from single color image. IEEE Transactions on Circuits and Systems for Video Technology (2018)
[8] Mueller, F., Mehta, D., Sotnychenko, O., Sridhar, S., Casas, D., Theobalt, C.: Real-time hand tracking under occlusion from an egocentric rgb-d sensor. In: Proceedings of International Conference on Computer Vision (ICCV) (2017)
[9] Zimmermann, C., Brox, T.: Learning to estimate 3d hand pose from single rgb images. arXiv preprint arXiv: 1705.01389 (2017)
[10] Zimmermann, C., Ceylan, D., Yang, J., Russell, B., Argus, M., Brox, T.: Freihand: A dataset for markerless capture of hand pose and shape from single rgb images. In: Proceedings of International Conference on Computer Vision (ICCV) (2019)
[11] Gomez-Donoso, F., Orts-Escolano, S., Cazorla, M.: Large-scale multiview 3d hand pose dataset. arXiv preprint arXiv:1707.03742 (2017)
[12] Mueller, F., Bernard, F., Sotnychenko, O., Mehta, D., Sridhar, S., Casas, D., Theobalt, C.: Ganerated hands for real-time 3d hand tracking from monocular rgb. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
[13] Simon, T., Joo, H., Matthews, I., Sheikh, Y.: Hand keypoint detection in single images using multiview bootstrapping. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
[14] Wu, W., Qian, C., Yang, S., Wang, Q., Cai, Y., Zhou, Q.: Look at boundary: A boundary-aware face alignment algorithm. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
[15] Koestinger, M., Wohlhart, P., Roth, P.M., Bischof, H.: Annotated facial landmarks in the wild: A large-scale, real-world database for facial landmark localization. In: IEEE International Conference on Computer Vision Workshop (2011)
[16] Burgos-Artizzu, X.P., Perona, P., Dolla ́r, P.: Robust face landmark estimation under occlusion. In: Proceedings of the 2013 IEEE International Conference on Computer Vision (2013)
[17] Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: 300 faces in-the-wild challenge: The first facial landmark localization challenge. In: IEEE International Conference on Computer Vision Workshop (2013)
[18] Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: Openpose: real- time multi-person 2d pose estimation using part affinity fields. arXiv preprint arXiv:1812.08008 (2018)
[19] Hidalgo, G., Raaj, Y., Idrees, H., Xiang, D., Joo, H., Simon, T., Sheikh, Y.: Single-network whole-body pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
[20] Cao,Z.,Simon,T.,Wei,S.E.,Sheikh,Y.:Realtimemulti-person2dposeestimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
[21] Newell, A., Huang, Z., Deng, J.: Associative embedding: End-to-end learning for joint detection and grouping. In: Advances in Neural Information Processing Systems (2017)
[22] Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. arXiv preprint arXiv:1902.09212 (2019)
[23] Honari, S., Yosinski, J., Vincent, P., Pal, C.: Recombinator networks: Learning coarse-to-fine feature aggregation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
[24] Kowalski,M.,Naruniec,J.,Trzcinski,T.:Deepalignmentnetwork:Aconvolutional neural network for robust face alignment. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop (2017)
[25] Valle, R., Buenaposada, J.M., Valdes, A., Baumela, L.: A deeply-initialized coarse- to-fine ensemble of regression trees for face alignment. In: Proceedings of the Eu- ropean Conference on Computer Vision (ECCV) (2018)
[26] Sun, K., Zhao, Y., Jiang, B., Cheng, T., Xiao, B., Liu, D., Mu, Y., Wang, X., Liu, W., Wang, J.: High-resolution representations for labeling pixels and regions. arXiv preprint arXiv:1904.04514 (2019)
[27] Fang, H.S., Li, J., Tang, H., Xu, C., Zhu, H., Li, Y., Xiu, Y., Lu, C.: https://github.com/Fang-Haoshu/Halpe-FullBody (2020)