Skip to main content

Learning to Fit Morphable Models

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13666))

Included in the following conference series:

Abstract

Fitting parametric models of human bodies, hands or faces to sparse input signals in an accurate, robust, and fast manner has the promise of significantly improving immersion in AR and VR scenarios. A common first step in systems that tackle these problems is to regress the parameters of the parametric model directly from the input data. This approach is fast, robust, and is a good starting point for an iterative minimization algorithm. The latter searches for the minimum of an energy function, typically composed of a data term and priors that encode our knowledge about the problem’s structure. While this is undoubtedly a very successful recipe, priors are often hand defined heuristics and finding the right balance between the different terms to achieve high quality results is a non-trivial task. Furthermore, converting and optimizing these systems to run in a performant way requires custom implementations that demand significant time investments from both engineers and domain experts. In this work, we build upon recent advances in learned optimization and propose an update rule inspired by the classic Levenberg-Marquardt algorithm. We show the effectiveness of the proposed neural optimizer on three problems, 3D body estimation from a head-mounted device, 3D body estimation from sparse 2D keypoints and face surface estimation from dense 2D landmarks. Our method can easily be applied to new model fitting problems and offers a competitive alternative to well-tuned ‘traditional’ model fitting pipelines, both in terms of accuracy and speed.

V. Choutas—Work performed at Microsoft.

F. Bogo—Now at Meta Reality Labs Research.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Adler, J., Öktem, O.: Solving ill-posed inverse problems using iterative deep neural networks. Inverse Prob. 33(12), 124007 (2017)

    Article  MathSciNet  MATH  Google Scholar 

  2. Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. In: NeurIPS, vol. 29. Curran Associates, Inc. (2016). https://proceedings.neurips.cc/paper/2016/file/fb87582825f9d28a8d42c5e5e5e8b23d-Paper.pdf

  3. Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: SCAPE: Shape Completion and Animation of People. ACM Trans. Graph. 24(3), 408–416 (2005). https://doi.org/10.1145/1073204.1073207

  4. Baek, S., Kim, K.I., Kim, T.K.: Pushing the envelope for RGB-based dense 3D hand pose estimation via neural rendering. In: Computer Vision and Pattern Recognition (CVPR), pp. 1067–1076, June 2019

    Google Scholar 

  5. Barron, J.T.: A general and adaptive robust loss function. In: Computer Vision and Pattern Recognition (CVPR), pp. 4326–4334, June 2019

    Google Scholar 

  6. Biggs, B., Novotny, D., Ehrhardt, S., Joo, H., Graham, B., Vedaldi, A.: 3D Multi-bodies: fitting sets of plausible 3d human models to ambiguous image data. In: NeurIPS, vol. 33, pp. 20496–20507. Curran Associates, Inc. (2020). https://proceedings.neurips.cc/paper/2020/file/ebf99bb5df6533b6dd9180a59034698d-Paper.pdf

  7. Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: ACM Transactions on Graphics (Proceedings of SIGGRAPH), pp. 187–194 (1999)

    Google Scholar 

  8. 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_34

    Chapter  Google Scholar 

  9. Boukhayma, A., Bem, R.d., Torr, P.H.: 3D hand shape and pose from images in the wild. In: Computer Vision and Pattern Recognition (CVPR), pp. 10843–10852, June 2019

    Google Scholar 

  10. Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: Openpose: realtime multi-person 2d pose estimation using part affinity fields. Trans. Pattern Anal. Mach. Intell. (TPAMI) 43(1), 172–186 (2021)

    Article  Google Scholar 

  11. Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734. Association for Computational Linguistics, Doha, Qatar, October 2014. https://doi.org/10.3115/v1/D14-1179, https://aclanthology.org/D14-1179

  12. Choi, H., Moon, G., Lee, K.M.: Beyond static features for temporally consistent 3D human pose and shape from a video. In: Computer Vision and Pattern Recognition (CVPR), pp. 1964–1973, June 2021

    Google Scholar 

  13. Choutas, V., Pavlakos, G., Bolkart, T., Tzionas, D., Black, M.J.: Monocular expressive body regression through body-driven attention. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 20–40. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58607-2_2

    Chapter  Google Scholar 

  14. Clark, R., Bloesch, M., Czarnowski, J., Leutenegger, S., Davison, A.J.: Learning to solve nonlinear least squares for monocular stereo. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 291–306. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_18

    Chapter  Google Scholar 

  15. Dehesa, J., Vidler, A., Padget, J., Lutteroth, C.: Grid-functioned neural networks. In: ICML, Proceedings of Machine Learning Research, vol. 139, pp. 2559–2567. PMLR, July 2021. https://proceedings.mlr.press/v139/dehesa21a.html

  16. Dittadi, A., Dziadzio, S., Cosker, D., Lundell, B., Cashman, T.J., Shotton, J.: Full-body motion from a single head-mounted device: generating SMPL poses from partial observations. In: International Conference on Computer Vision (ICCV), pp. 11687–11697, October 2021

    Google Scholar 

  17. Dong, Z., Song, J., Chen, X., Guo, C., Hilliges, O.: Shape-aware Multi-Person Pose Estimation from Multi-View Images. In: International Conference on Computer Vision (ICCV), pp. 11158–11168, October 2021

    Google Scholar 

  18. Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(7), 2121–2159 (2011)

    MathSciNet  MATH  Google Scholar 

  19. Egger, B., et al.: 3d morphable face models - past, present and future. ACM Trans. Graph. 39(5), 1–38 (2020). https://doi.org/10.1145/3395208

  20. Fan, T., Alwala, K.V., Xiang, D., Xu, W., Murphey, T., Mukadam, M.: Revitalizing optimization for 3d human pose and shape estimation: a sparse constrained formulation. In: International Conference on Computer Vision (ICCV), pp. 11457–11466, October 2021

    Google Scholar 

  21. Feng, Y., Choutas, V., Bolkart, T., Tzionas, D., Black, M.J.: Collaborative regression of expressive bodies using moderation. In: International Conference on 3D Vision (3DV), pp. 792–804 (2021)

    Google Scholar 

  22. Flynn, J., et al.: DeepView view synthesis with learned gradient descent. In: Computer Vision and Pattern Recognition (CVPR), pp. 2367–2376, June 2019

    Google Scholar 

  23. Guzov, V., Mir, A., Sattler, T., Pons-Moll, G.: Human POSEitioning system (HPS): 3D human pose estimation and self-localization in large scenes from body-mounted sensors. In: Computer Vision and Pattern Recognition (CVPR), pp. 4318–4329, June 2021

    Google Scholar 

  24. Hassan, M., Choutas, V., Tzionas, D., Black, M.J.: Resolving 3D human pose ambiguities with 3D scene constraints. In: International Conference on Computer Vision (ICCV), pp. 2282–2292, October 2019. https://prox.is.tue.mpg.de

  25. Hasson, Y., et al.: Learning joint reconstruction of hands and manipulated objects. In: Computer Vision and Pattern Recognition (CVPR), pp. 11807–11816, June 2019

    Google Scholar 

  26. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition, CVPR, pp. 770–778, June 2016

    Google Scholar 

  27. Holden, D., Komura, T., Saito, J.: Phase-functioned neural networks for character control. ACM Trans. Graph. 36(4), 1–3 (2017). https://doi.org/10.1145/3072959.3073663, https://doi.org/10.1145/3072959.3073663

  28. Igel, C., Toussaint, M., Weishui, W.: RPROP using the natural gradient. In: Trends and Applications in Constructive Approximation, pp. 259–272. Birkhäuser Basel, Basel (2005)

    Google Scholar 

  29. Ioffe, S., Szegedy, C.: Batch normalization training : accelerating deep network by reducing internal covariate shift. In: ICLR, pp. 448–456. PMLR (2015)

    Google Scholar 

  30. Joo, H., Neverova, N., Vedaldi, A.: Exemplar fine-tuning for 3d human pose fitting towards in-the-wild 3d human pose estimation. In: International Conference on 3D Vision (3DV), pp. 42–52 (2021)

    Google Scholar 

  31. Joo, H., Simon, T., Sheikh, Y.: Total capture: a 3D deformation model for tracking faces, hands, and bodies. In: Computer Vision and Pattern Recognition (CVPR), pp. 8320–8329, June 2018

    Google Scholar 

  32. Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: Computer Vision and Pattern Recognition (CVPR), pp. 7122–7131, June 2018

    Google Scholar 

  33. Kaufmann, M., et al.: EM-POSE: 3D human pose estimation from sparse electromagnetic trackers. In: International Conference on Computer Vision (ICCV), pp. 11510–11520, October 2021

    Google Scholar 

  34. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015). https://arxiv.org/abs/1412.6980

  35. Kocabas, M., Athanasiou, N., Black, M.J.: VIBE: video inference for human body pose and shape estimation. In: Computer Vision and Pattern Recognition (CVPR), pp. 5252–5262, June 2020

    Google Scholar 

  36. Kocabas, M., Huang, C.H.P., Hilliges, O., Black, M.J.: PARE: Part attention regressor for 3D human body estimation. In: International Conference on Computer Vision (ICCV), pp. 11127–11137, October 2021

    Google Scholar 

  37. Kokkinos, F., Kokkinos, I.: To The Point: Correspondence-driven monocular 3D category reconstruction. In: NeurIPS (2021). https://openreview.net/forum?id=AWMU04iXQ08

  38. Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via Model-Fitting in the loop. In: International Conference on Computer Vision (ICCV), pp. 2252–2261, October 2019

    Google Scholar 

  39. Kolotouros, N., Pavlakos, G., Jayaraman, D., Daniilidis, K.: Probabilistic modeling for human mesh recovery. In: International Conference on Computer Vision (ICCV), pp. 11585–11594, October 2021

    Google Scholar 

  40. Levenberg, K.: A method for the solution of certain non-linear problems in least squares. Q. Appl. Math. 2(2), 164–168 (1944)

    Article  MathSciNet  MATH  Google Scholar 

  41. Li, J., Xu, C., Chen, Z., Bian, S., Yang, L., Lu, C.: HybrIK: a hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation. In: Computer Vision and Pattern Recognition (CVPR), pp. 3383–3393, June 2021

    Google Scholar 

  42. Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (Proc. SIGGRAPH Asia). 34(6), 248:1–248:16 (2015)

    Google Scholar 

  43. Lv, Z., Dellaert, F., Rehg, J.M., Geiger, A.: Taking a deeper look at the inverse compositional algorithm. In: Computer Vision and Pattern Recognition (CVPR), pp. 4581–4590, June 2019

    Google Scholar 

  44. Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: AMASS: archive of motion capture as surface shapes. In: International Conference on Computer Vision (ICCV), pp. 5442–5451, October 2019

    Google Scholar 

  45. 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_37

    Chapter  Google Scholar 

  46. Marquardt, D.W.: An algorithm for least-squares estimation of nonlinear parameters. J. Soc. Ind. Appl. Math. 11(2), 431–441 (1963)

    Article  MathSciNet  MATH  Google Scholar 

  47. Mueller, F., et al.: Real-time pose and shape reconstruction of two interacting hands with a single depth camera. ACM Trans. Graph. 38(4), 1–13 (2019). https://doi.org/10.1145/3306346.3322958

  48. Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML (2010)

    Google Scholar 

  49. Nocedal, J., Wright, S.J.: Numerical Optimization, 2nd edn. Springer, New YorK (2006). https://doi.org/10.1007/978-0-387-40065-5

    Book  MATH  Google Scholar 

  50. Patel, P., Huang, C.H.P., Tesch, J., Hoffmann, D.T., Tripathi, S., Black, M.J.: AGORA: avatars in geography optimized for regression analysis. In: Computer Vision and Pattern Recognition (CVPR), pp. 13463–13473, June 2021

    Google Scholar 

  51. Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: Computer Vision and Pattern Recognition (CVPR), pp. 10975–10985, June 2019

    Google Scholar 

  52. Powell, M.J.D.: A hybrid method for nonlinear equations. In: Numerical Methods for Nonlinear Algebraic Equations. Gordon and Breach (1970)

    Google Scholar 

  53. Rempe, D., Birdal, T., Hertzmann, A., Yang, J., Sridhar, S., Guibas, L.J.: HuMoR: 3d human motion model for robust pose estimation. In: International Conference on Computer Vision (ICCV), pp. 11468–11479, October 2021

    Google Scholar 

  54. Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. ACM Trans. Graph. (Proc. SIGGRAPH Asia).<error l="302" c="Undefined command " />36(6), 1–13 (2017)

    Google Scholar 

  55. Rong, Y., Shiratori, T., Joo, H.: FrankMocap: a monocular 3d whole-body pose estimation system via regression and integration. In: International Conference on Computer Vision Workshops (ICCVw), October 2021

    Google Scholar 

  56. Schmidhuber, J.: Learning to control fast-weight memories: an alternative to dynamic recurrent networks. Neural Comput. 4(1), 131–139 (1992)

    Article  Google Scholar 

  57. Schmidhuber, J.: A neural network that embeds its own meta-levels. In: IEEE International Conference on Neural Networks, pp. 407–412. IEEE (1993)

    Google Scholar 

  58. Seeber, M., Poranne, R., Polleyfeyes, M., Oswald, M.: RealisticHands: a hybrid model for 3d hand reconstruction. In: International Conference on 3D Vision (3DV), pp. 22–31, December 2021

    Google Scholar 

  59. Shen, J., et al.: The Phong surface: efficient 3d model fitting using lifted optimization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 687–703. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_40

    Chapter  Google Scholar 

  60. Song, J., Chen, X., Hilliges, O.: Human body model fitting by learned gradient descent. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 744–760. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58565-5_44

    Chapter  Google Scholar 

  61. Srivastava, R.K., Greff, K., Schmidhuber, J.: Training very deep networks. In: NeurIPS, vol. 28. Curran Associates, Inc. (2015). https://proceedings.neurips.cc/paper/2015/file/215a71a12769b056c3c32e7299f1c5ed-Paper.pdf

  62. Taylor, J., et al.: Efficient and precise interactive hand tracking through joint, continuous optimization of pose and correspondences. ACM Trans. Graph. 35(4), 1–2 (2016). https://doi.org/10.1145/2897824.2925965, https://doi.org/10.1145/2897824.2925965

  63. Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., Nießner, M.: Face2Face: real-time face capture and reenactment of RGB videos. In: Computer Vision and Pattern Recognition (CVPR), pp. 2387–2395, June 2016

    Google Scholar 

  64. Tomè, D.,et al.: SelfPose: 3D egocentric pose estimation from a headset mounted camera. Trans. Pattern Anal. Mach. Intell. (TPAMI), 1 (2020). https://doi.org/10.1109/TPAMI.2020.3029700

  65. Tome, D., Peluse, P., Agapito, L., Badino, H.: xR-EgoPose: egocentric 3D human pose from an HMD camera. In: International Conference on Computer Vision (ICCV), pp. 7728–7738, October 2019

    Google Scholar 

  66. Vogel, C., Pock, T.: A primal dual network for low-level vision problems. In: Roth, V., Vetter, T. (eds.) GCPR 2017. LNCS, vol. 10496, pp. 189–202. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66709-6_16

    Chapter  Google Scholar 

  67. Wood, E., et al.: Fake it till you make it: face analysis in the wild using synthetic data alone. In: International Conference on Computer Vision (ICCV), pp. 3681–3691, October 2021

    Google Scholar 

  68. Xiang, D., Joo, H., Sheikh, Y.: Monocular total capture: posing face, body, and hands in the wild. In: Computer Vision and Pattern Recognition (CVPR), pp. 10965–10974, June 2019

    Google Scholar 

  69. Xie, K., Wang, T., Iqbal, U., Guo, Y., Fidler, S., Shkurti, F.: Physics-based human motion estimation and synthesis from videos. In: International Conference on Computer Vision (ICCV), pp. 11532–11541, October 2021

    Google Scholar 

  70. Xiong, X., De la Torre, F.: Supervised descent method and its applications to face alignment. In: Computer Vision and Pattern Recognition (CVPR), pp. 532–539, June 2013

    Google Scholar 

  71. Xu, H., Bazavan, E.G., Zanfir, A., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: GHUM & GHUML: Generative 3D human shape and articulated pose models. In: Computer Vision and Pattern Recognition (CVPR), pp. 6183–6192, June 2020

    Google Scholar 

  72. Yang, D., Kim, D., Lee, S.H.: LoBSTr: real-time lower-body pose prediction from sparse upper-body tracking signals. Comput. Graph. Forum (2021). https://doi.org/10.1111/cgf.142631

    Article  Google Scholar 

  73. Yuan, Y., Kitani, K.: Ego-pose estimation and forecasting as real-time PD control. In: International Conference on Computer Vision (ICCV), pp. 10082–10092, October 2019

    Google Scholar 

  74. Yuan, Y., Kitani, K.: 3D ego-pose estimation via imitation learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 763–778. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01270-0_45

    Chapter  Google Scholar 

  75. Yuan, Y., Wei, S.E., Simon, T., Kitani, K., Saragih, J.: SimPoE: simulated character control for 3d human pose estimation. In: Computer Vision and Pattern Recognition (CVPR), pp. 7159–7169, June 2021

    Google Scholar 

  76. Zach, C.: Robust bundle adjustment revisited. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 772–787. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_50

    Chapter  Google Scholar 

  77. Zanfir, A., Bazavan, E.G., Zanfir, M., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: Neural Descent for Visual 3D Human Pose and Shape. In: Computer Vision and Pattern Recognition (CVPR), pp. 14484–14493, June 2021

    Google Scholar 

  78. Zhang, H., et al: PyMAF: 3D human pose and shape regression with pyramidal mesh alignment feedback loop. In: International Conference on Computer Vision (ICCV), pp. 11446–11456, October 2021

    Google Scholar 

  79. Zhang, S., Zhang, Y., Bogo, F., Marc, P., Tang, S.: Learning motion priors for 4d human body capture in 3d scenes. In: International Conference on Computer Vision (ICCV), pp. 11343–11353, October 2021

    Google Scholar 

  80. Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: Computer Vision and Pattern Recognition (CVPR). pp. 5738–5746, June 2019

    Google Scholar 

  81. Zollhöfer, M., et al.: State of the art on monocular 3D face reconstruction, tracking, and applications. In: Computer Graphics Forum, vol. 37, pp. 523–550. Wiley Online Library (2018)

    Google Scholar 

Download references

Acknowledgement

We thank Pashmina Cameron, Sadegh Aliakbarian, Tom Cashman, Darren Cosker and Andrew Fitzgibbon for valuable discussions and proof reading.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Vasileios Choutas .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1616 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Choutas, V., Bogo, F., Shen, J., Valentin, J. (2022). Learning to Fit Morphable Models. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13666. Springer, Cham. https://doi.org/10.1007/978-3-031-20068-7_10

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20068-7_10

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20067-0

  • Online ISBN: 978-3-031-20068-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics