Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

DeciWatch: A Simple Baseline for \(10\times \) Efficient 2D and 3D Pose Estimation

  • 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

This paper proposes a simple baseline framework for video-based 2D/3D human pose estimation that can achieve \(10\times \) efficiency improvement over existing works without any performance degradation, named DeciWatch . Unlike current solutions that estimate each frame in a video, DeciWatch introduces a simple yet effective sample-denoise-recover framework that only watches sparsely sampled frames, taking advantage of the continuity of human motions and the lightweight pose representation. Specifically, DeciWatch uniformly samples less than \(10\%\) video frames for detailed estimation, denoises the estimated 2D/3D poses with an efficient Transformer architecture, and then accurately recovers the rest of the frames using another Transformer-based network. Comprehensive experimental results on three video-based human pose estimation, body mesh recovery tasks and efficient labeling in videos with four datasets validate the efficiency and effectiveness of DeciWatch. Code is available at https://github.com/cure-lab/DeciWatch.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /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

Notes

  1. 1.

    Due to the limit of pages, we present data description, comprehensive results of different sampling ratios, the effect of hyper-parameters, generalization ability, qualitative results, and failure cases analyses in the supplementary material.

References

  1. Burke, M., Lasenby, J.: Estimating missing marker positions using low dimensional kalman smoothing. J. Biomech. 49(9), 1854–1858 (2016)

    Article  Google Scholar 

  2. Cai, Y., et al.: A unified 3d human motion synthesis model via conditional variational auto-encoder. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 11645–11655 (2021)

    Google Scholar 

  3. Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: Openpose: realtime multi-person 2d pose estimation using part affinity fields. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 172–186 (2019)

    Article  Google Scholar 

  4. Choi, S., Choi, S., Kim, C.: Mobilehumanpose: toward real-time 3d human pose estimation in mobile devices. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2328–2338 (2021)

    Google Scholar 

  5. Chu, H., et al.: Part-aware measurement for robust multi-view multi-human 3d pose estimation and tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 1472–1481 (2021)

    Google Scholar 

  6. Dai, H., Shi, H., Liu, W., Wang, L., Liu, Y., Mei, T.: Fasterpose: a faster simple baseline for human pose estimation. arXiv preprint arXiv:2107.03215 (2021)

  7. Desmarais, Y., Mottet, D., Slangen, P., Montesinos, P.: A review of 3d human pose estimation algorithms for markerless motion capture. Comput. Vis. Image Underst. 212, 103275 (2021)

    Google Scholar 

  8. Duan, Y., et al.: Single-shot motion completion with transformer. arXiv preprint arXiv:2103.00776 (2021)

  9. Fan, Z., Liu, J., Wang, Y.: Adaptive computationally efficient network for monocular 3D hand pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 127–144. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58548-8_8

    Chapter  Google Scholar 

  10. Fan, Z., Liu, J., Wang, Y.: Motion adaptive pose estimation from compressed videos. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 11719–11728 (2021)

    Google Scholar 

  11. Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4346–4354 (2015)

    Google Scholar 

  12. Gløersen, Ø., Federolf, P.: Predicting missing marker trajectories in human motion data using marker intercorrelations. PLoS One, 11(3), e0152616 (2016)

    Google Scholar 

  13. Gundavarapu, N.B., Srivastava, D., Mitra, R., Sharma, A., Jain, A.: Structured aleatoric uncertainty in human pose estimation. In: CVPR Workshops, vol. 2, p. 2 (2019)

    Google Scholar 

  14. Harvey, F.G., Pal, C.: Recurrent transition networks for character locomotion. In: SIGGRAPH Asia 2018 Technical Briefs, pp. 1–4 (2018)

    Google Scholar 

  15. Harvey, F.G., Yurick, M., Nowrouzezahrai, D., Pal, C.: Robust motion in-betweening. ACM Trans. Graph. (TOG) 39(4), 60–1 (2020)

    Article  Google Scholar 

  16. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  17. Hernandez, A., Gall, J., Moreno-Noguer, F.: Human motion prediction via spatio-temporal inpainting. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7134–7143 (2019)

    Google Scholar 

  18. Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)

  19. Ho, H.I., Chen, X., Song, J., Hilliges, O.: Render in-between: Motion guided video synthesis for action interpolation. arXiv preprint arXiv:2111.01029 (2021)

  20. Howarth, S.J., Callaghan, J.P.: Quantitative assessment of the accuracy for three interpolation techniques in kinematic analysis of human movement. Comput. Meth. Biomech. Biomed. Eng. 13(6), 847–855 (2010)

    Article  Google Scholar 

  21. Hwang, D.H., Kim, S., Monet, N., Koike, H., Bae, S.: Lightweight 3d human pose estimation network training using teacher-student learning. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 479–488 (2020)

    Google Scholar 

  22. Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6 m: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325–1339 (2013)

    Article  Google Scholar 

  23. Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3192–3199 (2013)

    Google Scholar 

  24. Ji, L., Liu, R., Zhou, D., Zhang, Q., Wei, X.: Missing data recovery for human mocap data based on a-lstm and ls constraint. In: 2020 IEEE 5th International Conference on Signal and Image Processing (ICSIP), pp. 729–734. IEEE (2020)

    Google Scholar 

  25. 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 

  26. 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 

  27. Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401–4410 (2019)

    Google Scholar 

  28. Kaufmann, M., Aksan, E., Song, J., Pece, F., Ziegler, R., Hilliges, O.: Convolutional autoencoders for human motion infilling. In: 2020 International Conference on 3D Vision (3DV), pp. 918–927. IEEE (2020)

    Google Scholar 

  29. Kocabas, M., Huang, C.H.P., Hilliges, O., Black, M.J.: Pare: part attention regressor for 3d human body estimation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 11127–11137 (2021)

    Google Scholar 

  30. 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 

  31. Kucherenko, T., Beskow, J., Kjellström, H.: A neural network approach to missing marker reconstruction in human motion capture. arXiv preprint arXiv:1803.02665 (2018)

  32. Lai, R.Y., Yuen, P.C., Lee, K.K.: Motion capture data completion and denoising by singular value thresholding. In: Eurographics (Short Papers), pp. 45–48 (2011)

    Google Scholar 

  33. Li, J., et al.: Human pose regression with residual log-likelihood estimation. In: ICCV (2021)

    Google Scholar 

  34. 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 (2021)

    Google Scholar 

  35. Li, Z., Ye, J., Song, M., Huang, Y., Pan, Z.: Online knowledge distillation for efficient pose estimation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 11740–11750 (2021)

    Google Scholar 

  36. Liu, W., Bao, Q., Sun, Y., Mei, T.: Recent advances in monocular 2d and 3d human pose estimation: A deep learning perspective. arXiv preprint arXiv:2104.11536 (2021)

  37. Luo, Y., et al.: Lstm pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5207–5215 (2018)

    Google Scholar 

  38. 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 

  39. 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 

  40. 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 

  41. Nie, X., Li, Y., Luo, L., Zhang, N., Feng, J.: Dynamic kernel distillation for efficient pose estimation in videos. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6942–6950 (2019)

    Google Scholar 

  42. Osokin, D.: Real-time 2d multi-person pose estimation on cpu: lightweight openpose. arXiv preprint arXiv:1811.12004 (2018)

  43. 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 

  44. Reda, H.E.A., Benaoumeur, I., Kamel, B., Zoubir, A.F.: Mocap systems and hand movement reconstruction using cubic spline. In: 2018 5th International Conference on Control, Decision and Information Technologies (CoDIT), pp. 1–5. IEEE (2018)

    Google Scholar 

  45. Shuai, H., Wu, L., Liu, Q.: Adaptively multi-view and temporal fusing transformer for 3d human pose estimation. arXiv preprint arXiv:2110.05092 (2021)

  46. Skurowski, P., Pawlyta, M.: Gap reconstruction in optical motion capture sequences using neural networks. Sensors 21(18), 6115 (2021)

    Article  Google Scholar 

  47. Sovrasov, V.: Flops counter for convolutional networks in pytorch framework (2022). https://github.com/sovrasov/flops-counter.pytorch, original-date: 2018–08-17T09:54:59Z

  48. 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 

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

    Google Scholar 

  50. Wu, Q., Boulanger, P.: Real-time estimation of missing markers for reconstruction of human motion. In: 2011 XIII Symposium on Virtual Reality, pp. 161–168. IEEE (2011)

    Google Scholar 

  51. Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 466–481 (2018)

    Google Scholar 

  52. Xu, J., et al.: Exploring versatile prior for human motion via motion frequency guidance. In: 2021 International Conference on 3D Vision (3DV), pp. 606–616. IEEE (2021)

    Google Scholar 

  53. Yan, S., Li, Z., Xiong, Y., Yan, H., Lin, D.: Convolutional sequence generation for skeleton-based action synthesis. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4394–4402 (2019)

    Google Scholar 

  54. Yu, C., et al.: Lite-hrnet: a lightweight high-resolution network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10440–10450 (2021)

    Google Scholar 

  55. Yuan, Y., Iqbal, U., Molchanov, P., Kitani, K., Kautz, J.: Glamr: global occlusion-aware human mesh recovery with dynamic cameras. arXiv preprint arXiv:2112.01524 (2021)

  56. 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 

  57. 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 

  58. Zeng, A., Yang, L., Ju, X., Li, J., Wang, J., Xu, Q.: Smoothnet: a plug-and-play network for refining human poses in videos. arXiv preprint arXiv:2112.13715 (2021)

  59. Zhang, Y., Wang, Y., Camps, O., Sznaier, M.: Key frame proposal network for efficient pose estimation in videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 609–625. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58520-4_36

    Chapter  Google Scholar 

  60. Zhang, Z., Tang, J., Wu, G.: Simple and lightweight human pose estimation. arXiv preprint arXiv:1911.10346 (2019)

  61. Zhao, L., Wang, N., Gong, C., Yang, J., Gao, X.: Estimating human pose efficiently by parallel pyramid networks. IEEE Trans. Image Process. 30, 6785–6800 (2021)

    Article  Google Scholar 

  62. Zheng, C., Mendieta, M., Wang, P., Lu, A., Chen, C.: A lightweight graph transformer network for human mesh reconstruction from 2d human pose. arXiv preprint arXiv:2111.12696 (2021)

  63. Zheng, C., et al.: Deep learning-based human pose estimation: a survey. arXiv preprint arXiv:2012.13392 (2020)

  64. Zheng, C., Zhu, S., Mendieta, M., Yang, T., Chen, C., Ding, Z.: 3d human pose estimation with spatial and temporal transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 11656–11665 (2021)

    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, and Shanghai AI Laboratory.

Author information

Authors and Affiliations

  1. The Chinese University of Hong Kong, Hong Kong, China

    Ailing Zeng, Xuan Ju, Ruiyuan Gao & Qiang Xu

  2. Sensetime Group Limited, Hong Kong, China

    Lei Yang & Xizhou Zhu

  3. Shanghai AI Laboratory, Shanghai, China

    Bo Dai

Authors
  1. Ailing Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xuan Ju
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lei Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ruiyuan Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xizhou Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Bo Dai
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Qiang Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qiang Xu .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 2589 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. et al. (2022). DeciWatch: A Simple Baseline for \(10\times \) Efficient 2D and 3D Pose Estimation. 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_35

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20065-6_35

  • 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

Search

Navigation