Skip to main content

DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13662))

Included in the following conference series:

Abstract

Deep learning greatly improved the realism of animatable human models by learning geometry and appearance from collections of 3D scans, template meshes, and multi-view imagery. High-resolution models enable photo-realistic avatars but at the cost of requiring studio settings not available to end users. Our goal is to create avatars directly from raw images without relying on expensive studio setups and surface tracking. While a few such approaches exist, those have limited generalization capabilities and are prone to learning spurious (chance) correlations between irrelevant body parts, resulting in implausible deformations and missing body parts on unseen poses. We introduce a three-stage method that induces two inductive biases to better disentangled pose-dependent deformation. First, we model correlations of body parts explicitly with a graph neural network. Second, to further reduce the effect of chance correlations, we introduce localized per-bone features that use a factorized volumetric representation and a new aggregation function. We demonstrate that our model produces realistic body shapes under challenging unseen poses and shows high-quality image synthesis. Our proposed representation strikes a better trade-off between model capacity, expressiveness, and robustness than competing methods. Project website: https://lemonatsu.github.io/danbo.

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

Similar content being viewed by others

Notes

  1. 1.

    Meta did not have access to the Human3.6M dataset.

References

  1. Adobe: Mixamo (2020). https://www.mixamo.com/

  2. Alldieck, T., Xu, H., Sminchisescu, C.: imghum: implicit generative models of 3D human shape and articulated pose. In: ICCV (2021)

    Google Scholar 

  3. Bagautdinov, T., et al.: Driving-signal aware full-body avatars. ACM TOG (Proc. SIGGRAPH) 40, 1–17 (2021)

    Google Scholar 

  4. Balan, A.O., Sigal, L., Black, M.J., Davis, J.E., Haussecker, H.W.: Detailed human shape and pose from images. In: CVPR, pp. 1–8 (2007)

    Google Scholar 

  5. Barron, J.T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., Srinivasan, P.P.: Mip-nerf: a multiscale representation for anti-aliasing neural radiance fields. In: ICCV (2021)

    Google Scholar 

  6. Bhatnagar, B.L., Sminchisescu, C., Theobalt, C., Pons-Moll, G.: Combining implicit function learning and parametric models for 3D human reconstruction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 311–329. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_19

    Chapter  Google Scholar 

  7. Bińkowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying mmd gans. In: ICLR (2018)

    Google Scholar 

  8. Burov, A., Nießner, M., Thies, J.: Dynamic surface function networks for clothed human bodies. In: ICCV (2021)

    Google Scholar 

  9. Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)

  10. Chen, X., Zheng, Y., Black, M.J., Hilliges, O., Geiger, A.: Snarf: differentiable forward skinning for animating non-rigid neural implicit shapes. In: ICCV (2021)

    Google Scholar 

  11. 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. https://expose.is.tue.mpg.de

  12. CMU Graphics Lab Motion Capture Database. http://mocap.cs.cmu.edu

  13. Computing, U.A.R.: Ubc arc sockeye (2019). https://doi.org/10.14288/SOCKEYE

  14. Corona, E., Pumarola, A., Alenyà, G., Pons-Moll, G., Moreno-Noguer, F.: Smplicit: topology-aware generative model for clothed people. In: CVPR (2021)

    Google Scholar 

  15. Deng, B., et al.: Nasa: neural articulated shape approximation. arXiv preprint arXiv:1912.03207 (2019)

  16. Gafni, G., Thies, J., Zollhöfer, M., Nießner, M.: Dynamic neural radiance fields for monocular 4D facial avatar reconstruction. In: CVPR (2021)

    Google Scholar 

  17. Gao, C., Saraf, A., Kopf, J., Huang, J.B.: Dynamic view synthesis from dynamic monocular video. In: ICCV (2021)

    Google Scholar 

  18. Gong, K., Liang, X., Li, Y., Chen, Y., Yang, M., Lin, L.: Instance-level human parsing via part grouping network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 805–822. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_47

    Chapter  Google Scholar 

  19. Guo, K., et al.: The relightables: volumetric performance capture of humans with realistic relighting. ACM TOG (Proc. SIGGRAPH) 38, 1–19 (2019)

    Google Scholar 

  20. Habermann, M., Liu, L., Xu, W., Zollhoefer, M., Pons-Moll, G., Theobalt, C.: Real-time deep dynamic characters. ACM TOG (Proc. SIGGRAPH) 40, 1–16 (2021)

    Google Scholar 

  21. Ionescu, C., Carreira, J., Sminchisescu, C.: Iterated second-order label sensitive pooling for 3D human pose estimation. In: CVPR (2014)

    Google Scholar 

  22. Ionescu, C., Li, F., Sminchisescu, C.: Latent structured models for human pose estimation. In: ICCV (2011)

    Google Scholar 

  23. Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)

    Google Scholar 

  24. Kocabas, M., Athanasiou, N., Black, M.J.: Vibe: video inference for human body pose and shape estimation. In: CVPR (2020)

    Google Scholar 

  25. Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: ICCV (2019)

    Google Scholar 

  26. Kwon, Y., Kim, D., Ceylan, D., Fuchs, H.: Neural human performer: learning generalizable radiance fields for human performance rendering. In: NeurIPS (2021)

    Google Scholar 

  27. Lin, C.H., Ma, W.C., Torralba, A., Lucey, S.: Barf: bundle-adjusting neural radiance fields. arXiv preprint arXiv:2104.06405 (2021)

  28. Lindell, D.B., Martel, J.N., Wetzstein, G.: Autoint: automatic integration for fast neural volume rendering. In: CVPR (2021)

    Google Scholar 

  29. Liu, L., Habermann, M., Rudnev, V., Sarkar, K., Gu, J., Theobalt, C.: Neural actor: neural free-view synthesis of human actors with pose control. ACM TOG (Proc. SIGGRAPH Asia) 40, 1–16 (2021)

    Google Scholar 

  30. Lombardi, S., Simon, T., Schwartz, G., Zollhoefer, M., Sheikh, Y., Saragih, J.: Mixture of volumetric primitives for efficient neural rendering. ACM TOG (Proc. SIGGRAPH) 40, 1–13 (2021)

    Google Scholar 

  31. Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: Smpl: a skinned multi-person linear model. ACM TOG (Proc. SIGGRAPH) 34(6), 1–16 (2015)

    Google Scholar 

  32. Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3D surface construction algorithm. ACM TOG (Proc. SIGGRAPH) 21, 163–169 (1987)

    Google Scholar 

  33. Mihajlovic, M., Saito, S., Bansal, A., Zollhoefer, M., Tang, S.: COAP: compositional articulated occupancy of people. In: CVPR (2022)

    Google Scholar 

  34. Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405–421. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_24

    Chapter  Google Scholar 

  35. Noguchi, A., Sun, X., Lin, S., Harada, T.: Neural articulated radiance field. In: ICCV (2021)

    Google Scholar 

  36. Osman, A.A.A., Bolkart, T., Black, M.J.: STAR: sparse trained articulated human body regressor. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 598–613. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58539-6_36

    Chapter  Google Scholar 

  37. Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: Deepsdf: learning continuous signed distance functions for shape representation. In: CVPR (2019)

    Google Scholar 

  38. Park, K., et al.: Hypernerf: a higher-dimensional representation for topologically varying neural radiance fields. ACM TOG (Proc. SIGGRAPH) (2021)

    Google Scholar 

  39. Parmar, G., Zhang, R., Zhu, J.Y.: On aliased resizing and surprising subtleties in gan evaluation. In: CVPR (2022)

    Google Scholar 

  40. Peng, S., et al.: Animatable neural radiance fields for modeling dynamic human bodies. In: ICCV (2021)

    Google Scholar 

  41. Peng, S., et al.: Neural body: implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. In: CVPR (2021)

    Google Scholar 

  42. Peng, S., Niemeyer, M., Mescheder, L., Pollefeys, M., Geiger, A.: Convolutional occupancy networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 523–540. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_31

    Chapter  Google Scholar 

  43. Pumarola, A., Corona, E., Pons-Moll, G., Moreno-Noguer, F.: D-NeRF: neural radiance fields for dynamic scenes. In: CVPR (2020)

    Google Scholar 

  44. Saito, S., Yang, J., Ma, Q., Black, M.J.: SCANimate: weakly supervised learning of skinned clothed avatar networks. In: CVPR (2021)

    Google Scholar 

  45. Sitzmann, V., Martel, J., Bergman, A., Lindell, D., Wetzstein, G.: Implicit neural representations with periodic activation functions. In: NeurIPS, vol. 33 (2020)

    Google Scholar 

  46. Su, S.Y., Yu, F., Zollhöfer, M., Rhodin, H.: A-nerf: articulated neural radiance fields for learning human shape, appearance, and pose. In: NeurIPS (2021)

    Google Scholar 

  47. Tiwari, G., Bhatnagar, B.L., Tung, T., Pons-Moll, G.: SIZER: a dataset and model for parsing 3D clothing and learning size sensitive 3D clothing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 1–18. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_1

    Chapter  Google Scholar 

  48. Tiwari, G., Sarafianos, N., Tung, T., Pons-Moll, G.: Neural-gif: neural generalized implicit functions for animating people in clothing. In: ICCV (2021)

    Google Scholar 

  49. Tretschk, E., Tewari, A., Golyanik, V., Zollhöfer, M., Lassner, C., Theobalt, C.: Non-rigid neural radiance fields: reconstruction and novel view synthesis of a dynamic scene from monocular video. In: ICCV (2021)

    Google Scholar 

  50. Varol, G., et al.: Learning from synthetic humans. In: CVPR (2017)

    Google Scholar 

  51. Wang, S., Mihajlovic, M., Ma, Q., Geiger, A., Tang, S.: Metaavatar: learning animatable clothed human models from few depth images. In: NeurIPS (2021)

    Google Scholar 

  52. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. TIP 13, 600–612 (2004)

    Google Scholar 

  53. Xian, W., Huang, J.B., Kopf, J., Kim, C.: Space-time neural irradiance fields for free-viewpoint video. In: CVPR (2021)

    Google Scholar 

  54. Xu, H., Alldieck, T., Sminchisescu, C.: H-nerf: neural radiance fields for rendering and temporal reconstruction of humans in motion. In: NeurIPS (2021)

    Google Scholar 

  55. 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: CVPR (2020)

    Google Scholar 

  56. Xu, W., et al.: Monoperfcap: human performance capture from monocular video. TOG 37(2), 27 (2018)

    Article  Google Scholar 

  57. Yen-Chen, L., Florence, P., Barron, J.T., Rodriguez, A., Isola, P., Lin, T.Y.: inerf: inverting neural radiance fields for pose estimation. In: IROS (2020)

    Google Scholar 

  58. Yu, A., Li, R., Tancik, M., Li, H., Ng, R., Kanazawa, A.: PlenOctrees for real-time rendering of neural radiance fields. In: ICCV (2021)

    Google Scholar 

  59. Yu, A., Ye, V., Tancik, M., Kanazawa, A.: pixelNeRF: neural radiance fields from one or few images. In: CVPR (2021)

    Google Scholar 

  60. Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)

    Google Scholar 

  61. Zhou, X., Zhu, M., Pavlakos, G., Leonardos, S., Derpanis, K.G., Daniilidis, K.: Monocap: monocular human motion capture using a cnn coupled with a geometric prior. PAMI 41, 901–914 (2018)

    Article  Google Scholar 

  62. Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: CVPR, pp. 5745–5753 (2019)

    Google Scholar 

Download references

Acknowledgment

Shih-Yang Su and Helge Rhodin were supported by Compute Canada, Advanced Research Computing at UBC [13], and NSERC DC.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Shih-Yang Su .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 5226 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

Su, SY., Bagautdinov, T., Rhodin, H. (2022). DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks. 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 13662. Springer, Cham. https://doi.org/10.1007/978-3-031-20086-1_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20086-1_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20085-4

  • Online ISBN: 978-3-031-20086-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics