Advertisement

Human Body Model Fitting by Learned Gradient Descent

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12365)

Abstract

We propose a novel algorithm for the fitting of 3D human shape to images. Combining the accuracy and refinement capabilities of iterative gradient-based optimization techniques with the robustness of deep neural networks, we propose a gradient descent algorithm that leverages a neural network to predict the parameter update rule for each iteration. This per-parameter and state-aware update guides the optimizer towards a good solution in very few steps, converging in typically few steps. During training our approach only requires MoCap data of human poses, parametrized via SMPL. From this data the network learns a subspace of valid poses and shapes in which optimization is performed much more efficiently. The approach does not require any hard to acquire image-to-3D correspondences. At test time we only optimize the 2D joint re-projection error without the need for any further priors or regularization terms. We show empirically that this algorithm is fast (avg. 120ms convergence), robust to initialization and dataset, and achieves state-of-the-art results on public evaluation datasets including the challenging 3DPW in-the-wild benchmark (improvement over SMPLify (\(45\%\)) and also approaches using image-to-3D correspondences).

Keywords

Human body fitting 3D human pose Inverse problem 

Notes

Acknowledgement

This research was partially supported by the Max Planck ETH Center for Learning Systems and a research gift from NVIDIA.

Supplementary material

504476_1_En_44_MOESM1_ESM.pdf (2 mb)
Supplementary material 1 (pdf 2069 KB)

References

  1. 1.
    Adler, J., Öktem, O.: Solving ill-posed inverse problems using iterative deep neural networks. Inverse Prob. 33(12), 124007 (2017)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Adler, J., Öktem, O.: Learned primal-dual reconstruction. IEEE Trans. Med. Imaging 37(6), 1322–1332 (2018)CrossRefGoogle Scholar
  3. 3.
    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, pp. 3686–3693 (2014)Google Scholar
  4. 4.
    Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. In: Advances in Neural Information Processing Systems, pp. 3981–3989 (2016)Google Scholar
  5. 5.
    Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: SCAPE: shape completion and animation of people. ACM Trans. Graph. (TOG) 24, 408–416 (2005)Google Scholar
  6. 6.
    Arnab, A., Doersch, C., Zisserman, A.: Exploiting temporal context for 3D human pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3395–3404 (2019)Google Scholar
  7. 7.
    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
  8. 8.
    Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: OpenPose: realtime multi-person 2D pose estimation using part affinity fields. arXiv preprint arXiv:1812.08008 (2018)
  9. 9.
    Flynn, J., et al.: DeepView: view synthesis with learned gradient descent. arXiv preprint arXiv:1906.07316 (2019)
  10. 10.
    Guan, P., Weiss, A., Balan, A.O., Black, M.J.: Estimating human shape and pose from a single image. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1381–1388. IEEE (2009)Google Scholar
  11. 11.
    Guler, R.A., Kokkinos, I.: HoloPose: holistic 3D human reconstruction in-the-wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10884–10894 (2019)Google Scholar
  12. 12.
    Hadamard, J.: Sur les problèmes aux dérivées partielles et leur signification physique. Princeton University Bulletin, pp. 49–52 (1902)Google Scholar
  13. 13.
    Hasler, N., Ackermann, H., Rosenhahn, B., Thormählen, T., Seidel, H.P.: Multilinear pose and body shape estimation of dressed subjects from image sets. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1823–1830. IEEE (2010)Google Scholar
  14. 14.
    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. Pattern Anal. Mach. Intell. 36(7), 1325–1339 (2013)Google Scholar
  15. 15.
    Joo, H., Simon, T., Sheikh, Y.: Total capture: a 3D deformation model for tracking faces, hands, and bodies. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8320–8329 (2018)Google Scholar
  16. 16.
    Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7122–7131 (2018)Google Scholar
  17. 17.
    Kanazawa, A., Zhang, J.Y., Felsen, P., Malik, J.: Learning 3D human dynamics from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5614–5623 (2019)Google Scholar
  18. 18.
    Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2252–2261 (2019)Google Scholar
  19. 19.
    Kolotouros, N., Pavlakos, G., Daniilidis, K.: Convolutional mesh regression for single-image human shape reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4501–4510 (2019)Google Scholar
  20. 20.
    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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6050–6059 (2017)Google Scholar
  21. 21.
    Loper, M., Mahmood, N., Black, M.J.: MoSH: motion and shape capture from sparse markers. ACM Trans. Graph. (TOG) 33(6), 220 (2014)CrossRefGoogle Scholar
  22. 22.
    Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (TOG) 34(6), 248 (2015)CrossRefGoogle Scholar
  23. 23.
    Mahmood, N., Ghorbani, N., F. Troje, N., Pons-Moll, G., Black, M.J.: AMASS: archive of motion capture as surface shapes. In: The IEEE International Conference on Computer Vision (ICCV), October 2019. https://amass.is.tue.mpg.de
  24. 24.
    von Marcard, T., Henschel, R., Black, M.J., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3D human pose in the wild using IMUs and a moving camera. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 614–631. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01249-6_37CrossRefGoogle Scholar
  25. 25.
    Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2640–2649 (2017)Google Scholar
  26. 26.
    Mehta, D., et al.: VNect: real-time 3D human pose estimation with a single RGB camera. ACM Trans. Graph. (TOG) 36(4), 44 (2017)CrossRefGoogle 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.
    Omran, M., Lassner, C., Pons-Moll, G., Gehler, P., Schiele, B.: Neural body fitting: unifying deep learning and model based human pose and shape estimation. In: 2018 International Conference on 3D Vision (3DV), pp. 484–494. IEEE (2018)Google Scholar
  29. 29.
    Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10975–10985 (2019)Google Scholar
  30. 30.
    Pavlakos, G., Zhu, L., Zhou, X., Daniilidis, K.: Learning to estimate 3D human pose and shape from a single color image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 459–468 (2018)Google Scholar
  31. 31.
    Pishchulin, L., et al.: DeepCut: joint subset partition and labeling for multi person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4929–4937 (2016)Google Scholar
  32. 32.
    Sigal, L., Balan, A., Black, M.J.: Combined discriminative and generative articulated pose and non-rigid shape estimation. In: Advances in Neural Information Processing Systems, pp. 1337–1344 (2008)Google Scholar
  33. 33.
    Sun, X., Xiao, B., Wei, F., Liang, S., Wei, Y.: Integral human pose regression. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 536–553. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01231-1_33CrossRefGoogle Scholar
  34. 34.
    Tan, V., Budvytis, I., Cipolla, R.: Indirect deep structured learning for 3D human body shape and pose prediction (2018)Google Scholar
  35. 35.
    Tung, H.Y., Tung, H.W., Yumer, E., Fragkiadaki, K.: Self-supervised learning of motion capture. In: Advances in Neural Information Processing Systems, pp. 5236–5246 (2017)Google Scholar
  36. 36.
    Varol, G., et al.: BodyNet: volumetric inference of 3D human body shapes. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 20–38. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01234-2_2CrossRefGoogle Scholar
  37. 37.
    Varol, G., et al.: Learning from synthetic humans. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 109–117 (2017)Google Scholar
  38. 38.
    Xiang, D., Joo, H., Sheikh, Y.: Monocular total capture: posing face, body, and hands in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10965–10974 (2019)Google Scholar
  39. 39.
    Xu, Y., Zhu, S.C., Tung, T.: DenseRaC: joint 3D pose and shape estimation by dense render-and-compare. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7760–7770 (2019)Google Scholar
  40. 40.
    Zheng, Z., Yu, T., Wei, Y., Dai, Q., Liu, Y.: DeepHuman: 3D human reconstruction from a single image. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7739–7749 (2019)Google Scholar
  41. 41.
    Zhou, X., Zhu, M., Leonardos, S., Derpanis, K.G., Daniilidis, K.: Sparseness meets deepness: 3D human pose estimation from monocular video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4966–4975 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.ETH ZürichZürichSwitzerland
  2. 2.Max Planck ETH Center for Learning SystemsZürichSwitzerland

Personalised recommendations