Abstract
Estimating 3D hand pose from 2D images is a difficult, inverse problem due to the inherent scale and depth ambiguities. Current state-of-the-art methods train fully supervised deep neural networks with 3D ground-truth data. However, acquiring 3D annotations is expensive, typically requiring calibrated multi-view setups or labour intensive manual annotations. While annotations of 2D keypoints are much easier to obtain, how to efficiently leverage such weakly-supervised data to improve the task of 3D hand pose prediction remains an important open question. The key difficulty stems from the fact that direct application of additional 2D supervision mostly benefits the 2D proxy objective but does little to alleviate the depth and scale ambiguities. Embracing this challenge we propose a set of novel losses that constrain the prediction of a neural network to lie within the range of biomechanically feasible 3D hand configurations. We show by extensive experiments that our proposed constraints significantly reduce the depth ambiguity and allow the network to more effectively leverage additional 2D annotated images. For example, on the challenging freiHAND dataset, using additional 2D annotation without our proposed biomechanical constraints reduces the depth error by only \(15\%\), whereas the error is reduced significantly by \(50\%\) when the proposed biomechanical constraints are used.
A. Spurr—This work was done during an internship at NVIDIA.
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
Albrecht, I., Haber, J., Seidel, H.P.: Construction and animation of anatomically based human hand models. In: SIGGRAPH (2003)
Aristidou, A.: Hand tracking with physiological constraints. Vis. Comput. 34(2), 213–228 (2018). https://doi.org/10.1007/s00371-016-1327-8
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)
Baek, S., Kim, K.I., Kim, T.K.: Pushing the envelope for RGB-based dense 3D hand pose estimation via neural rendering. In: CVPR (2019)
Boukhayma, A., de Bem, R., Torr, P.H.: 3D hand shape and pose from images in the wild. In: CVPR (2019)
Cai, Y., Ge, L., Cai, J., Yuan, J.: Weakly-supervised 3D hand pose estimation from monocular RGB images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 678–694. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_41
Cai, Y., et al.: Exploiting spatial-temporal relationships for 3D pose estimation via graph convolutional networks. In: CVPR (2019)
Cerveri, P., De Momi, E., Lopomo, N., Baud-Bovy, G., Barros, R., Ferrigno, G.: Finger kinematic modeling and real-time hand motion estimation. Ann. Biomed. Eng. 35(11), 1989–2002 (2007). https://doi.org/10.1007/s10439-007-9364-0
Chen Chen, F., Appendino, S., Battezzato, A., Favetto, A., Mousavi, M., Pescarmona, F.: Constraint study for a hand exoskeleton: human hand kinematics and dynamics. J. Robot. (2013)
Cobos, S., Ferre, M., Uran, M.S., Ortego, J., Pena, C.: Efficient human hand kinematics for manipulation tasks. In: IROS (2008)
Cordella, F., Zollo, L., Guglielmelli, E., Siciliano, B.: A bio-inspired grasp optimization algorithm for an anthropomorphic robotic hand. Int. J. Interact. Des. Manuf. 6(2), 113–122 (2012). https://doi.org/10.1007/s12008-012-0149-9
Dibra, E., Wolf, T., Oztireli, C., Gross, M.: How to refine 3D hand pose estimation from unlabelled depth data? In: 3DV (2017)
Ge, L., et al.: 3D hand shape and pose estimation from a single RGB image. In: CVPR (2019)
Hampali, S., Rad, M., Oberweger, M., Lepetit, V.: HOnnotate: a method for 3D annotation of hand and object poses. In: CVPR (2020)
Hasson, Y.,et al.: Learning joint reconstruction of hands and manipulated objects. In: CVPR (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Heap, T., Hogg, D.: Towards 3D hand tracking using a deformable model. In: FG (1996)
Iqbal, U., Molchanov, P., Breuel, T., Gall, J., Kautz, J.: Hand pose estimation via latent 2.5D heatmap regression. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 125–143. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_8
Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: CVPR (2018)
Kuch, J.J., Huang, T.S.: Vision based hand modeling and tracking for virtual teleconferencing and telecollaboration. In: CVPR (1995)
Kulon, D., Wang, H., Güler, R.A., Bronstein, M., Zafeiriou, S.: Single image 3D hand reconstruction with mesh convolutions. In: BMVC (2019)
Lee, J., Kunii, T.L.: Model-based analysis of hand posture. IEEE Comput. Graph. Appl. 15(5), 77–86 (1995)
Lin, J., Wu, Y., Huang, T.S.: Modeling the constraints of human hand motion. In: IEEE Workshop on Human Motion (2000)
Melax, S., Keselman, L., Orsten, S.: Dynamics based 3D skeletal hand tracking. In: ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (2013)
Mueller, F., et al.: GANerated hands for real-time 3D hand tracking from monocular RGB. In: CVPR (2018)
Oikonomidis, I., Kyriazis, N., Argyros, A.A.: Full DOF tracking of a hand interacting with an object by modeling occlusions and physical constraints. In: ICCV (2011)
Oikonomidis, I., Kyriazis, N., Argyros, A.A.: Efficient model-based 3D tracking of hand articulations using kinect. In: BMVC (2011)
Panteleris, P., Oikonomidis, I., Argyros, A.: Using a single RGB frame for real time 3D hand pose estimation in the wild. In: WACV (2017)
Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: CVPR (2019)
Reed, N.: What is the simplest way to compute principal curvature for a mesh triangle? (2019). https://computergraphics.stackexchange.com/questions/1718/what-is-the-simplest-way-to-compute-principal-curvature-for-a-mesh-triangle
Rhee, T., Neumann, U., Lewis, J.P.: Human hand modeling from surface anatomy. In: ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (2006)
Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. In: SIGGRAPH-Asia (2017)
Ryf, C., Weymann, A.: The neutral zero method–a principle of measuring joint function. Injury 26, 1–11 (1995)
Spurr, A., Song, J., Park, S., Hilliges, O.: Cross-modal deep variational hand pose estimation. In: CVPR (2018)
Sridhar, S., Mueller, F., Zollhöfer, M., Casas, D., Oulasvirta, A., Theobalt, C.: Real-time joint tracking of a hand manipulating an object from RGB-D input. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 294–310. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_19
Sridhar, S., Oulasvirta, A., Theobalt, C.: Interactive markerless articulated hand motion tracking using RGB and depth data. In: ICCV (2013)
Sun, X., Shang, J., Liang, S., Wei, Y.: Compositional human pose regression. In: ICCV (2017)
Tekin, B., Bogo, F., Pollefeys, M.: H+o: unified egocentric recognition of 3D hand-object poses and interactions. In: CVPR (2019)
Tompson, J., Stein, M., Lecun, Y., Perlin, K.: Real-time continuous pose recovery of human hands using convolutional networks. ACM Trans. Graph. (ToG) 33(5), 1–10 (2014)
Wan, C., Probst, T., Gool, L.V., Yao, A.: Self-supervised 3D hand pose estimation through training by fitting. In: CVPR (2019)
Wu, Y., Huang, T.S.: Capturing articulated human hand motion: a divide-and-conquer approach. In: ICCV (1999)
Xiang, D., Joo, H., Sheikh, Y.: Monocular total capture: posing face, body, and hands in the wild. In: CVPR (2019)
Xu, C., Cheng, L.: Efficient hand pose estimation from a single depth image. In: ICCV (2013)
Yang, L., Yao, A.: Disentangling latent hands for image synthesis and pose estimation. In: CVPR (2019)
Zhang, J., Jiao, J., Chen, M., Qu, L., Xu, X., Yang, Q.: 3D hand pose tracking and estimation using stereo matching. arXiv:1610.07214 (2016)
Zhang, X., Li, Q., Mo, H., Zhang, W., Zheng, W.: End-to-end hand mesh recovery from a monocular RGB image. In: ICCV (2019)
Zhou, X., Huang, Q., Sun, X., Xue, X., Wei, Y.: Towards 3D human pose estimation in the wild: a weakly-supervised approach. In: ICCV (2017)
Zimmermann, C., Brox, T.: Learning to estimate 3D hand pose from single RGB images. In: ICCV (2017)
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: ICCV (2019)
Acknowledgments
We are grateful to Christoph Gebhardt and Shoaib Ahmed Siddiqui for the aid in figure creation and Abhishek Badki for helpful discussions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Spurr, A., Iqbal, U., Molchanov, P., Hilliges, O., Kautz, J. (2020). Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12362. Springer, Cham. https://doi.org/10.1007/978-3-030-58520-4_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-58520-4_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58519-8
Online ISBN: 978-3-030-58520-4
eBook Packages: Computer ScienceComputer Science (R0)