Abstract
We introduce DOPE, the first method to detect and estimate whole-body 3D human poses, including bodies, hands and faces, in the wild. Achieving this level of details is key for a number of applications that require understanding the interactions of the people with each other or with the environment. The main challenge is the lack of in-the-wild data with labeled whole-body 3D poses. In previous work, training data has been annotated or generated for simpler tasks focusing on bodies, hands or faces separately. In this work, we propose to take advantage of these datasets to train independent experts for each part, namely a body, a hand and a face expert, and distill their knowledge into a single deep network designed for whole-body 2D-3D pose detection. In practice, given a training image with partial or no annotation, each part expert detects its subset of keypoints in 2D and 3D and the resulting estimations are combined to obtain whole-body pseudo ground-truth poses. A distillation loss encourages the whole-body predictions to mimic the experts’ outputs. Our results show that this approach significantly outperforms the same whole-body model trained without distillation while staying close to the performance of the experts. Importantly, DOPE is computationally less demanding than the ensemble of experts and can achieve real-time performance. Test code and models are available at https://europe.naverlabs.com/research/computer-vision/dope.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: CVPR (2014)
Armagan, A., et al.: Measuring generalisation to unseen viewpoints, articulations, shapes and objects for 3D hand pose estimation under hand-object interaction. In: ECCV (2020)
Arnab, A., Doersch, C., Zisserman, A.: Exploiting temporal context for 3D human pose estimation in the wild. In: CVPR (2019)
Bhardwaj, S., Srinivasan, M., Khapra, M.M.: Efficient video classification using fewer frames. In: CVPR (2019)
Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: SIGGRAPH (1999)
Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep it SMPL: automatic estimation of 3D human pose and shape from a single image. In: ECCV (2016)
Booth, J., Roussos, A., Zafeiriou, S., Ponniahy, A., Dunaway, D.: A 3D morphable model learnt from 10,000 faces. In: CVPR (2016)
Boukhayma, A., de Bem, R., Torr, P.H.S.: 3D hand shape and pose from images in the wild. In: CVPR (2019)
Bulat, A., Tzimiropoulos, G.: How far are we from solving the 2D & 3D face alignment problem? (and a dataset of 230,000 3D facial landmarks). In: ICCV (2017)
Cai, Y., Ge, L., Cai, J., Yuan, J.: Weakly-supervised 3D hand pose estimation from monocular RGB images. In: ECCV (2018)
Cao, C., Weng, Y., Zhou, S., Tong, Y., Zhou, K.: FaceWarehouse: a 3D facial expression database for visual computing. IEEE Trans. Vis. Comput. Graph. 20(3), 413–425 (2013)
Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: OpenPose: realtime multi-person 2D pose estimation using Part Affinity Fields. In: arXiv preprint arXiv:1812.08008 (2018)
Chen, C.H., Ramanan, D.: 3D human pose estimation = 2D pose estimation + matching. In: CVPR (2017)
Chen, G., Choi, W., Yu, X., Han, T., Chandraker, M.: Learning efficient object detection models with knowledge distillation. In: NeurIPS (2017)
Cimen, G., Maurhofer, C., Sumner, B., Guay, M.: AR poser: automatically augmenting mobile pictures with digital avatars imitating poses. In: CGVCVIP (2018)
Crasto, N., Weinzaepfel, P., Alahari, K., Schmid, C.: MARS: motion-augmented RGB stream for action recognition. In: CVPR (2019)
Crispell, D., Bazik, M.: Pix2Face: direct 3D face model estimation. In: ICCV Workshop (2017)
Deng, J., et al.: The Menpo benchmark for multi-pose 2D and 3D facial landmark localisation and tracking. IJCV 127(6–7), 599–624 (2019)
Fang, H.S., Xie, S., Tai, Y.W., Lu, C.: RMPE: regional multi-person pose estimation. In: ICCV (2017)
Feng, Y., Wu, F., Shao, X., Wang, Y., Zhou, X.: Joint 3D face reconstruction and dense alignment with position map regression network. In: ECCV (2020)
Garcia-Salguero, M., Gonzalez-Jimenez, J., Moreno, F.A.: Human 3D pose estimation with a tilting camera for social mobile robot interaction. Sensors 19(22), 4943 (2019)
Ge, L., et al.: 3D hand shape and pose estimation from a single RGB image. In: CVPR (2019)
Gui, L.Y., Zhang, K., Wang, Y.X., Liang, X., Moura, J.M., Veloso, M.: Teaching robots to predict human motion. In: IROS (2018)
Habibie, I., Xu, W., Mehta, D., Pons-Moll, G., Theobalt, C.: In the wild human pose estimation using explicit 2D features and intermediate 3D representations. In: CVPR (2019)
Hampali, S., Rad, M., Oberweger, M., Lepetit, V.: Honnotate: a method for 3D annotation of hand and objects poses. In: CVPR (2020)
Hasson, Y., et al.: Learning joint reconstruction of hands and manipulated objects. In: CVPR (2019)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Hidalgo, G., et al.: Single-network whole-body pose estimation. In: ICCV (2019)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Workshop (2014)
Hoffman, J., Gupta, S., Darrell, T.: Learning with side information through modality hallucination. In: CVPR (2016)
Hou, S., Pan, X., Change Loy, C., Wang, Z., Lin, D.: Lifelong learning via progressive distillation and retrospection. In: ECCV (2018)
Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. PAMI 36(7), 1325–1339 (2013)
Jackson, A.S., Bulat, A., Argyriou, V., Tzimiropoulos, G.: Large pose 3D face reconstruction from a single image via direct volumetric CNN regression. In: ICCV (2017)
Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: BMVC (2010)
Johnson, S., Everingham, M.: Learning effective human pose estimation from inaccurate annotation. In: CVPR (2011)
Joo, H., Simon, T., Sheikh, Y.: Total capture: a 3D deformation model for tracking faces, hands, and bodies. In: CVPR (2018)
Lassner, C., Romero, J., Kiefel, M., Bogo, F., Black, M.J., Gehler, P.V.: Unite the people: closing the loop between 3D and 2D human representations. In: CVPR (2017)
Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: ICML Workshop (2013)
Li, T., Bolkart, T., Black, M.J., Li, H., Romero, J.: Learning a model of facial shape and expression from 4D scans. ACM Trans. Graph. (ToG) 36(6), 194 (2017)
Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV (2014)
Liu, X., He, P., Chen, W., Gao, J.: Improving multi-task deep neural networks via knowledge distillation for natural language understanding. arXiv preprint arXiv:1904.09482 (2019)
Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. 34(6), 1–16 (2015)
Lopez-Paz, D., Bottou, L., Schölkopf, B., Vapnik, V.: Unifying distillation and privileged information. In: ICLR (2016)
Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3D human pose estimation. In: ICCV (2017)
Mehta, D., et al.: Single-shot multi-person 3D pose estimation from monocular RGB. In: 3DV (2018)
Mehta, D., et al.: VNect: real-time 3D human pose estimation with a single RGB camera. ACM Trans. Graph. 36(4), 1–14 (2017)
Moon, G., Chang, J.Y., Lee, K.M.: Camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. In: ICCV (2019)
Mueller, F., et al.: GANerated hands for real-time 3D hand tracking from monocular RGB. In: CVPR (2018)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)
Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: CVPR (2019)
Pavlakos, G., Zhou, X., Derpanis, K.G., Daniilidis, K.: Coarse-to-fine volumetric prediction for single-image 3D human pose. In: CVPR (2017)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)
Rogez, G., Schmid, C.: Mocap-guided data augmentation for 3D pose estimation in the wild. In: NIPS (2016)
Rogez, G., Weinzaepfel, P., Schmid, C.: LCR-Net++: multi-person 2D and 3D pose detection in natural images. IEEE Trans. PAMI 42(5), 1146–1161 (2019)
Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. ACM Trans. Graph. 36(6), 245 (2017)
Sanyal, S., Bolkart, T., Feng, H., Black, M.J.: Learning to regress 3D face shape and expression from an image without 3D supervision. In: CVPR (2019)
Simon, T., Joo, H., Matthews, I., Sheikh, Y.: Hand keypoint detection in single images using multiview bootstrapping. In: CVPR (2017)
Spurr, A., Song, J., Park, S., Hilliges, O.: Cross-modal deep variational hand pose estimation. In: CVPR (2018)
Supančič, J.S., Rogez, G., Yang, Y., Shotton, J., Ramanan, D.: Depth-based hand pose estimation: methods, data, and challenges. IJCV 126(11), 1180–1198 (2018)
Vapnik, V., Izmailov, R.: Learning using privileged information: similarity control and knowledge transfer. JMLR 16(1), 2023–2049 (2015)
Varol, G., et al.: Learning from synthetic humans. In: CVPR (2017)
Wu, Y., Ji, Q.: Facial landmark detection: a literature survey. IJCV 127(2), 115–142 (2019)
Xiang, D., Joo, H., Sheikh, Y.: Monocular total capture: Posing face, body, and hands in the wild. In: CVPR (2019)
Xiong, P., Li, G., Sun, Y.: Combining local and global features for 3D face tracking. In: ICCV Workshops (2017)
Yang, L., Li, S., Lee, D., Yao, A.: Aligning latent spaces for 3D hand pose estimation. In: ICCV (2019)
Yuan, S., Stenger, B., Kim, T.K.: RGB-based 3D hand pose estimation via privileged learning with depth images. arXiv preprint arXiv:1811.07376 (2018)
Zadeh, A., Baltrusaitis, T., Morency, L.P.: Convolutional experts constrained local model for facial landmark detection. In: CVPR Workshop (2017)
Zafeiriou, S., Chrysos, G., Roussos, A., Ververas, E., Deng, J., Trigeorgis, G.: The 3D menpo facial landmark tracking challenge. In: ICCV Workshops (2017)
Zhang, J., Jiao, J., Chen, M., Qu, L., Xu, X., Yang, Q.: A hand pose tracking benchmark from stereo matching. In: ICIP (2017)
Zhang, X., Li, Q., Mo, H., Zhang, W., Zheng, W.: End-to-end hand mesh recovery from a monocular RGB image. In: ICCV (2019)
Zhu, X., Liu, X., Lei, Z., Li, S.Z.: Face alignment in full pose range: a 3D total solution. IEEE Trans. PAMI 41(1), 78–92 (2017)
Zimmermann, C., Brox, T.: Learning to estimate 3D hand pose from single RGB images. In: ICCV (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Weinzaepfel, P., Brégier, R., Combaluzier, H., Leroy, V., Rogez, G. (2020). DOPE: Distillation of Part Experts for Whole-Body 3D Pose Estimation in the Wild. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12371. Springer, Cham. https://doi.org/10.1007/978-3-030-58574-7_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-58574-7_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58573-0
Online ISBN: 978-3-030-58574-7
eBook Packages: Computer ScienceComputer Science (R0)