Advertisement

Hand Pose Estimation via Latent 2.5D Heatmap Regression

  • Umar IqbalEmail author
  • Pavlo Molchanov
  • Thomas Breuel
  • Juergen Gall
  • Jan Kautz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11215)

Abstract

Estimating the 3D pose of a hand is an essential part of human-computer interaction. Estimating 3D pose using depth or multi-view sensors has become easier with recent advances in computer vision, however, regressing pose from a single RGB image is much less straightforward. The main difficulty arises from the fact that 3D pose requires some form of depth estimates, which are ambiguous given only an RGB image. In this paper we propose a new method for 3D hand pose estimation from a monocular image through a novel 2.5D pose representation. Our new representation estimates pose up to a scaling factor, which can be estimated additionally if a prior of the hand size is given. We implicitly learn depth maps and heatmap distributions with a novel CNN architecture. Our system achieves state-of-the-art accuracy for 2D and 3D hand pose estimation on several challenging datasets in presence of severe occlusions.

Keywords

Hand pose 2D to 3D 3D reconstruction 2.5D heatmaps 

Notes

Acknowledgements

JG was supported by the ERC Starting Grant ARCA.

Supplementary material

474198_1_En_8_MOESM1_ESM.pdf (1.1 mb)
Supplementary material 1 (pdf 1101 KB)

References

  1. 1.
    Rehg, J.M., Kanade, T.: Visual tracking of high DOF articulated structures: an application to human hand tracking. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 801, pp. 35–46. Springer, Heidelberg (1994).  https://doi.org/10.1007/BFb0028333CrossRefGoogle Scholar
  2. 2.
    de Campos, T.E., Murray, D.W.: Regression-based hand pose estimation from multiple cameras. In: CVPR (2006)Google Scholar
  3. 3.
    Oikonomidis, I., Kyriazis, N., Argyros, A.A.: Markerless and efficient 26-DOF hand pose recovery. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, vol. 6494, pp. 744–757. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-19318-7_58CrossRefGoogle Scholar
  4. 4.
    Rosales, R., Athitsos, V., Sigal, L., Sclaroff, S.: 3D hand pose reconstruction using specialized mappings. In: ICCV (2001)Google Scholar
  5. 5.
    Ballan, L., Taneja, A., Gall, J., Van Gool, L., Pollefeys, M.: Motion capture of hands in action using discriminative salient points. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 640–653. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33783-3_46CrossRefGoogle Scholar
  6. 6.
    Sridhar, S., Rhodin, H., Seidel, H.P., Oulasvirta, A., Theobalt, C.: Real-time hand tracking using a sum of anisotropic Gaussians model. In: 3DV (2014)Google Scholar
  7. 7.
    Tzionas, D., Ballan, L., Srikantha, A., Aponte, P., Pollefeys, M., Gall, J.: Capturing hands in action using discriminative salient points and physics simulation. IJCV 118, 172–193 (2016)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Panteleris, P., Argyros, A.: Back to RGB: 3D tracking of hands and hand-object interactions based on short-baseline stereo. arXiv preprint arXiv:1705.05301 (2017)
  9. 9.
    Romero, J., Tzionas, D., Black, M.J.: Embodied hands: Modeling and capturing hands and bodies together. In: SIGGRAPH Asia (2017)Google Scholar
  10. 10.
    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)Google Scholar
  11. 11.
    Xu, C., Cheng, L.: Efficient hand pose estimation from a single depth image. In: ICCV (2013)Google Scholar
  12. 12.
    Qian, C., Sun, X., Wei, Y., Tang, X., Sun, J.: Realtime and robust hand tracking from depth. In: CVPR (2014)Google Scholar
  13. 13.
    Taylor, J., et al.: User-specific hand modeling from monocular depth sequences. In: CVPR (2014)Google Scholar
  14. 14.
    Tang, D., Chang, H.J., Tejani, A., Kim, T.K.: Latent regression forest: structured estimation of 3D articulated hand posture. In: CVPR (2014)Google Scholar
  15. 15.
    Tompson, J., Stein, M., Lecun, Y., Perlin, K.: Real-time continuous pose recovery of human hands using convolutional networks. ToG 33, 169 (2014)CrossRefGoogle Scholar
  16. 16.
    Tang, D., Taylor, J., Kohli, P., Keskin, C., Kim, T.K., Shotton, J.: Opening the black box: hierarchical sampling optimization for estimating human hand pose. In: ICCV 2015)Google Scholar
  17. 17.
    Makris, A., Kyriazis, N., Argyros, A.A.: Hierarchical particle filtering for 3D hand tracking. In: CVPR (2015)Google Scholar
  18. 18.
    Sridhar, S., Mueller, F., Oulasvirta, A., Theobalt, C.: Fast and robust hand tracking using detection-guided optimization. In: CVPR (2015)Google Scholar
  19. 19.
    Sun, X., Wei, Y., Liang, S., Tang, X., Sun, J.: Cascaded hand pose regression. In: CVPR (2015)Google Scholar
  20. 20.
    Oberweger, M., Wohlhart, P., Lepetit, V.: Training a feedback loop for hand pose estimation. In: ICCV (2015)Google Scholar
  21. 21.
    Oberweger, M., Riegler, G., Wohlhart, P., Lepetit, V.: Efficiently creating 3D training data for fine hand pose estimation. In: CVPR (2016)Google Scholar
  22. 22.
    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_19CrossRefGoogle Scholar
  23. 23.
    Yuan, S., et al.: Depth-based 3d hand pose estimation: from current achievements to future goals. In: IEEE CVPR (2018)Google Scholar
  24. 24.
    Oikonomidis, I., Kyriazis, N., Argyros, A.A.: Efficient model-based 3d tracking of hand articulations using kinect. In: BMVC, vol. 1, p. 3 (2011)Google Scholar
  25. 25.
    Wang, R.Y., Popović, J.: Real-time hand-tracking with a color glove. ToG 28, 63 (2009)Google Scholar
  26. 26.
    Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: CVPR (2016)Google Scholar
  27. 27.
    Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483–499. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46484-8_29CrossRefGoogle Scholar
  28. 28.
    Toshev, A., Szegedy, C.: Deeppose: human pose estimation via deep neural networks. In: CVPR (2014)Google Scholar
  29. 29.
    Sun, X., Shang, J., Liang, S., Wei, Y.: Compositional human pose regression. In: ICCV (2017)Google Scholar
  30. 30.
    Pavlakos, G., Zhou, X., Derpanis, K.G., Daniilidis, K.: Coarse-to-fine volumetric prediction for single-image 3D human pose. In: CVPR (2017)Google Scholar
  31. 31.
    Heap, T., Hogg, D.: Towards 3D hand tracking using a deformable model. In: FG (1996)Google Scholar
  32. 32.
    Wu, Y., Lin, J.Y., Huang, T.S.: Capturing natural hand articulation. In: ICCV (2001)Google Scholar
  33. 33.
    Sigal, L., Balan, A.O., Black, M.J.: HumanEva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. IJCV 87(1), 4–27 (2010)CrossRefGoogle Scholar
  34. 34.
    de La Gorce, M., Fleet, D.J., Paragios, N.: Model-based 3D hand pose estimation from monocular video. TPAMI 33, 1793–1805 (2011)CrossRefGoogle Scholar
  35. 35.
    Lu, S., Metaxas, D., Samaras, D., Oliensis, J.: Using multiple cues for hand tracking and model refinement. In: CVPR (2003)Google Scholar
  36. 36.
    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: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 561–578. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46454-1_34CrossRefGoogle Scholar
  37. 37.
    Panteleris, P., Oikonomidis, I., Argyros, A.: Using a single RGB frame for real time 3D hand pose estimation in the wild. In: WACV (2018)Google Scholar
  38. 38.
    Athitsos, V., Sclaroff, S.: Estimating 3D hand pose from a cluttered image. In: CVPR (2003)Google Scholar
  39. 39.
    Romero, J., Kjellström, H., Kragic, D.: Hands in action: real-time 3D reconstruction of hands in interaction with objects. In: ICRA (2010)Google Scholar
  40. 40.
    Chen, C., Ramanan, D.: 3D human pose estimation = 2D pose estimation + matching. In: CVPR (2017)Google Scholar
  41. 41.
    Iqbal, U., Doering, A., Yasin, H., Krüger, B., Weber, A., Gall, J.: A dual-source approach for 3D pose estimation in single images. CVIU (2018, in Press)Google Scholar
  42. 42.
    Ramakrishna, V., Kanade, T., Sheikh, Y.: Reconstructing 3D human pose from 2D image landmarks. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 573–586. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33765-9_41CrossRefGoogle Scholar
  43. 43.
    Simo-Serra, E., Quattoni, A., Torras, C., Moreno-Noguer, F.: A joint model for 2D and 3D pose estimation from a single image. In: CVPR (2013)Google Scholar
  44. 44.
    Akhter, I., Black, M.J.: Pose-conditioned joint angle limits for 3D human pose reconstruction. In: CVPR (2015)Google Scholar
  45. 45.
    Tome, D., Russell, C., Agapito, L.: Lifting from the deep: convolutional 3D pose estimation from a single image. In: CVPR (2017)Google Scholar
  46. 46.
    Moreno-Noguer, F.: 3D human pose estimation from a single image via distance matrix regression. In: CVPR (2017)Google Scholar
  47. 47.
    Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3D human pose estimation. In: ICCV (2017)Google Scholar
  48. 48.
    Zimmermann, C., Brox, T.: Learning to estimate 3D hand pose from single RGB images. In: ICCV (2017)Google Scholar
  49. 49.
    Tekin, B., Marquez-Neila, P., Salzmann, M., Fua, P.: Learning to fuse 2D and 3D image cues for monocular body pose estimation. In: ICCV (2017)Google Scholar
  50. 50.
    Li, S., Chan, A.B.: 3D human pose estimation from monocular images with deep convolutional neural network. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9004, pp. 332–347. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-16808-1_23CrossRefGoogle Scholar
  51. 51.
    Zhou, X., Sun, X., Zhang, W., Liang, S., Wei, Y.: Deep kinematic pose regression. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 186–201. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-49409-8_17CrossRefGoogle Scholar
  52. 52.
    Mueller, F., et al.: GANerated hands for real-time 3D hand tracking from monocular RGB. In: CVPR (2018)Google Scholar
  53. 53.
    Spurr, A., Song, J., Park, S., Hilliges, O.: Cross-modal deep variational hand pose estimation. In: CVPR (2018)Google Scholar
  54. 54.
    Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)Google Scholar
  55. 55.
    Popa, A., Zanfir, M., Sminchisescu, C.: Deep multitask architecture for integrated 2D and 3D human sensing. In: CVPR (2017)Google Scholar
  56. 56.
    Zhou, X., Huang, Q., Sun, X., Xue, X., Wei, Y.: Weakly-supervised transfer for 3D human pose estimation in the wild. In: ICCV (2017)Google Scholar
  57. 57.
    Nie, B.X., Wei, P., Zhu, S.C.: Monocular 3D human pose estimation by predicting depth on joints. In: ICCV (2017)Google Scholar
  58. 58.
    Mehta, D., et al.: VNect: real-time 3D human pose estimation with a single RGB camera. In: SIGGRAPH (2017)CrossRefGoogle Scholar
  59. 59.
    Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: CVPR (2015)Google Scholar
  60. 60.
    Simon, T., Joo, H., Matthews, I., Sheikh, Y.: Hand keypoint detection in single images using multiview bootstrapping. In: CVPR (2017)Google Scholar
  61. 61.
    Chapelle, O., Wu, M.: Gradient descent optimization of smoothed information retrieval metrics. Inf. Retr. 13, 216–235 (2010)CrossRefGoogle Scholar
  62. 62.
    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: ICCV (2017)Google Scholar
  63. 63.
    Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746–760. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33715-4_54CrossRefGoogle Scholar
  64. 64.
    Zhang, J., Jiao, J., Chen, M., Qu, L., Xu, X., Yang, Q.: 3D hand pose tracking and estimation using stereo matching. arXiv preprint arXiv:1610.07214 (2016)
  65. 65.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  66. 66.
    Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: CVPR (2017)Google Scholar
  67. 67.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Umar Iqbal
    • 1
    • 2
    Email author
  • Pavlo Molchanov
    • 1
  • Thomas Breuel
    • 1
  • Juergen Gall
    • 2
  • Jan Kautz
    • 1
  1. 1.NVIDIASanta ClaraUSA
  2. 2.University of BonnBonnGermany

Personalised recommendations