Skip to main content

SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13665))

Included in the following conference series:

Abstract

When analyzing human motion videos, the output jitters from existing pose estimators are highly-unbalanced with varied estimation errors across frames. Most frames in a video are relatively easy to estimate and only suffer from slight jitters. In contrast, for rarely seen or occluded actions, the estimated positions of multiple joints largely deviate from the ground truth values for a consecutive sequence of frames, rendering significant jitters on them.

To tackle this problem, we propose to attach a dedicated temporal-only refinement network to existing pose estimators for jitter mitigation, named SmoothNet. Unlike existing learning-based solutions that employ spatio-temporal models to co-optimize per-frame precision and temporal smoothness at all the joints, SmoothNet models the natural smoothness characteristics in body movements by learning the long-range temporal relations of every joint without considering the noisy correlations among joints. With a simple yet effective motion-aware fully-connected network, SmoothNet improves the temporal smoothness of existing pose estimators significantly and enhances the estimation accuracy of those challenging frames as a side-effect. Moreover, as a temporal-only model, a unique advantage of SmoothNet is its strong transferability across various types of estimators, modalities, and datasets. Comprehensive experiments on five datasets with eleven popular backbone networks across 2D and 3D pose estimation and body recovery tasks demonstrate the efficacy of the proposed solution. Code is available at https://github.com/cure-lab/SmoothNet.

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

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

References

  1. 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 

  2. Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv arXiv:abs/1803.01271 (2018)

  3. Brownrigg, D.R.: The weighted median filter. Commun. ACM 27(8), 807–818 (1984)

    Article  Google Scholar 

  4. Casiez, G., Roussel, N., Vogel, D.: 1€ filter: a simple speed-based low-pass filter for noisy input in interactive systems. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 2527–2530 (2012)

    Google Scholar 

  5. Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7103–7112 (2018)

    Google Scholar 

  6. Choi, H., Moon, G., Chang, J.Y., Lee, K.M.: Beyond static features for temporally consistent 3D human pose and shape from a video. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1964–1973 (2021)

    Google Scholar 

  7. 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 

  8. Coskun, H., Achilles, F., DiPietro, R.S., Navab, N., Tombari, F.: Long short-term memory kalman filters: recurrent neural estimators for pose regularization. 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5525–5533 (2017)

    Google Scholar 

  9. Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)

  10. Fischman, M.G.: Programming time as a function of number of movement parts and changes in movement direction. J. Mot. Behav. 16(4), 405–423 (1984)

    Article  Google Scholar 

  11. Gauss, J.F., Brandin, C., Heberle, A., Löwe, W.: Smoothing skeleton avatar visualizations using signal processing technology. SN Comput. Sci. 2(6), 1–17 (2021)

    Article  Google Scholar 

  12. Hunter, J.S.: The exponentially weighted moving average. J. Qual. Technol. 18(4), 203–210 (1986)

    Article  Google Scholar 

  13. Hyndman, R.J.: Moving averages (2011)

    Google Scholar 

  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. Jiang, T., Camgoz, N.C., Bowden, R.: Skeletor: skeletal transformers for robust body-pose estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3394–3402 (2021)

    Google Scholar 

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

    Google Scholar 

  17. Kalman, R.E.: A new approach to linear filtering and prediction problems (1960)

    Google Scholar 

  18. 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 

  19. Kanazawa, A., Zhang, J.Y., Felsen, P., Malik, J.: Learning 3D human dynamics from video. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5614–5623 (2019)

    Google Scholar 

  20. Kim, D.Y., Chang, J.Y.: Attention-based 3D human pose sequence refinement network. Sensors 21(13), 4572 (2021)

    Article  Google Scholar 

  21. Kocabas, M., Athanasiou, N., Black, M.J.: Vibe: video inference for human body pose and shape estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5253–5263 (2020)

    Google Scholar 

  22. 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/CVF International Conference on Computer Vision, pp. 2252–2261 (2019)

    Google Scholar 

  23. Lee, C.H., Lin, C.R., Chen, M.S.: Sliding-window filtering: an efficient algorithm for incremental mining. In: Proceedings of the Tenth International Conference on Information and Knowledge Management, pp. 263–270 (2001)

    Google Scholar 

  24. Li, J., Bian, S., Zeng, A., Wang, C., Pang, B., Liu, W., Lu, C.: Human pose regression with residual log-likelihood estimation. In: ICCV (2021)

    Google Scholar 

  25. Li, R., Yang, S., Ross, D.A., Kanazawa, A.: AI choreographer: music conditioned 3D dance generation with AIST++. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 13401–13412, October 2021

    Google Scholar 

  26. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  27. Luo, Z., Golestaneh, S.A., Kitani, K.M.: 3D human motion estimation via motion compression and refinement. In: Proceedings of the Asian Conference on Computer Vision (2020)

    Google Scholar 

  28. 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: Proceedings of the European Conference on Computer Vision (ECCV), pp. 601–617 (2018)

    Google Scholar 

  29. 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 

  30. Mehta, D., et al.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 2017 International Conference on 3D Vision (3DV), pp. 506–516. IEEE (2017)

    Google Scholar 

  31. Mehta, D., et al.: XNect: real-time multi-person 3D motion capture with a single RGB camera. ACM Trans. Graph. (TOG) 39(4), 82-1 (2020)

    Google Scholar 

  32. Mehta, D., et al.: Single-shot multi-person 3D pose estimation from monocular RGB. In: 2018 International Conference on 3D Vision (3DV), pp. 120–130 (2018)

    Google Scholar 

  33. Mehta, D., et al.: VNect: real-time 3D human pose estimation with a single RGB camera. ACM Trans. Graph. (TOG) 36(4), 1–14 (2017)

    Article  Google Scholar 

  34. 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_29

    Chapter  Google Scholar 

  35. Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7753–7762 (2019)

    Google Scholar 

  36. Press, W.H., Teukolsky, S.A.: Savitzky-Golay smoothing filters. Comput. Phys. 4(6), 669–672 (1990)

    Article  Google Scholar 

  37. So, D., Le, Q., Liang, C.: The evolved transformer. In: International Conference on Machine Learning, pp. 5877–5886. PMLR (2019)

    Google Scholar 

  38. Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693–5703 (2019)

    Google Scholar 

  39. Tripathi, S., Ranade, S., Tyagi, A., Agrawal, A.: Posenet3d: learning temporally consistent 3D human pose via knowledge distillation. In: 2020 International Conference on 3D Vision (3DV), pp. 311–321. IEEE (2020)

    Google Scholar 

  40. Tsuchida, S., Fukayama, S., Hamasaki, M., Goto, M.: AIST dance video database: multi-genre, multi-dancer, and multi-camera database for dance information processing. In: ISMIR, pp. 501–510 (2019)

    Google Scholar 

  41. Van Loan, C.: Computational frameworks for the fast Fourier transform. SIAM (1992)

    Google Scholar 

  42. Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)

    Google Scholar 

  43. Véges, M., Lőrincz, A.: Temporal smoothing for 3D human pose estimation and localization for occluded people. In: Yang, H., Pasupa, K., Leung, A.C.-S., Kwok, J.T., Chan, J.H., King, I. (eds.) ICONIP 2020. LNCS, vol. 12532, pp. 557–568. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-63830-6_47

    Chapter  Google Scholar 

  44. Wan, Z., Li, Z., Tian, M., Liu, J., Yi, S., Li, H.: Encoder-decoder with multi-level attention for 3D human shape and pose estimation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 13033–13042 (2021)

    Google Scholar 

  45. Wang, J., Yan, S., Xiong, Y., Lin, D.: Motion guided 3D pose estimation from videos. arXiv abs/2004.13985 (2020)

    Google Scholar 

  46. Young, I.T., Van Vliet, L.J.: Recursive implementation of the gaussian filter. Signal Process. 44(2), 139–151 (1995)

    Article  Google Scholar 

  47. Zeng, A., Sun, X., Huang, F., Liu, M., Xu, Q., Lin, S.: SRNet: improving generalization in 3D human pose estimation with a split-and-recombine approach. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 507–523. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_30

    Chapter  Google Scholar 

  48. Zeng, A., Sun, X., Yang, L., Zhao, N., Liu, M., Xu, Q.: Learning skeletal graph neural networks for hard 3D pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision (2021)

    Google Scholar 

  49. Zhang, S., Zhang, Y., Bogo, F., Pollefeys, M., Tang, S.: Learning motion priors for 4D human body capture in 3D scenes. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 11343–11353 (2021)

    Google Scholar 

  50. Zhao, L., Peng, X., Tian, Y., Kapadia, M., Metaxas, D.N.: Semantic graph convolutional networks for 3D human pose regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3425–3435 (2019)

    Google Scholar 

  51. Zheng, C., Zhu, S., Mendieta, M., Yang, T., Chen, C., Ding, Z.: 3D human pose estimation with spatial and temporal transformers. arXiv preprint arXiv:2103.10455 (2021)

  52. Zhou, H., et al.: Informer: beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of AAAI (2021)

    Google Scholar 

  53. Zhou, K., Bhatnagar, B.L., Lenssen, J.E., Pons-Moll, G.: TOCH: spatio-temporal object correspondence to hand for motion refinement. arXiv, May 2022

    Google Scholar 

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

    Google Scholar 

Download references

Acknowledgement

This work is supported in part by Shenzhen-Hong Kong-Macau Science and Technology Program (Category C) of Shenzhen Science Technology and Innovation Commission under Grant No. SGDX2020110309500101.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Qiang Xu .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 520 KB)

Supplementary material 2 (pdf 8014 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

Zeng, A., Yang, L., Ju, X., Li, J., Wang, J., Xu, Q. (2022). SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos. 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 13665. Springer, Cham. https://doi.org/10.1007/978-3-031-20065-6_36

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20065-6_36

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20064-9

  • Online ISBN: 978-3-031-20065-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics