[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

An improved \(\ell _1\) median model for extracting 3D human body curve-skeleton

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Three-dimensional human body curve-skeleton is widely used in pose estimation, skeleton animation and other fields. This paper proposes an improved \(\ell _1\) median model that can extract three-dimensional human body curve-skeleton. The model includes three-dimensional human body reconstruction from multi-view images, interpolation curve-skeleton extraction, \(\ell _1\) median skeleton completion, and continuous frame curve-skeleton optimization. Through the completion and optimization processes, the curve-skeleton we extract is smoother and more complete compared with previous methods. We conduct experiments on multi-view human body image dataset collected from light field acquisition system. Both quantitative and qualitative results demonstrate the effectiveness of our model.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17

Similar content being viewed by others

References

  1. Au KC, Tai CL, Chu HK, Cohen-Or D, Lee TY (2008) Skeleton extraction by mesh contraction. ACM Trans Graph 27(3):1–10

    Article  Google Scholar 

  2. Avron H, Sharf A, Chen G, Cohen-Or D (2010) \(\ell _1\) - Sparse reconstruction of sharp point set surfaces. ACM Trans Graph 29(5):1–12

  3. Baran I, Popović J (2007) Automatic rigging and animation of 3D characters. ACM Trans Graph 26(3):72

    Article  Google Scholar 

  4. Benzine A, Chabot F, Luvison B, Pham Q, Achard C (2020) PandaNet: anchor-based single-shot multi-person 3D pose estimation. Comput Vis Pattern Recognit pp 6855–6864

  5. Blum H (1973) Biological shape and visual science (part I). J Theor Biol pp 205–287

  6. Cao J, Tagliasacchi A, Olson M, Zhang H, Su Z (2010) Point cloud skeletons via laplacian based contraction. In Shape Modeling International Conference, IEEE, pp 187–197

  7. Chuang J-H, Ahuja N, Lin C-C, Tsai C-H, Chen C-H (2004) A potential-based generalized cylinder representation. Comput Graph 28(6):907–918

    Article  Google Scholar 

  8. De Aguiar E, Theobalt C, Thrun S, Seidel H-P (2008) Automatic conversion of mesh animations into skeleton-based animations. Comput Graphics Forum 27(2):389–397

    Article  Google Scholar 

  9. Dey TK, Sun J (2006) Defining and computing curve-skeletons with medial geodesic function. Symposium on Geometry Processing 6:143–152

    Google Scholar 

  10. Furukawa Y, Ponce J (2010) Accurate, dense, and robust multiview stereopsis. IEEE Trans Pattern Anal Mach Intell 32(8):1362–1376

    Article  Google Scholar 

  11. Hilaga M, Shinagawa Y, Komura T, Kunii TL (2001) Topology matching for fully automatic similarity estimation of 3D shapes. In ACM SIGGRAPH pp 203–212

  12. Huang H, Wu S, Cohen-Or D, Gong M, Zhang H, Li G, Chen B (2013) L1-medial skeleton of point cloud. ACM Trans Graph 32(4):1–8

    MATH  Google Scholar 

  13. James DL, Twigg CD (2005) Skinning mesh animations. ACM Trans Graph 24:399–407

    Article  Google Scholar 

  14. Katz S, Tal A (2003) Hierarchical mesh decomposition using fuzzy clustering and cuts. ACM Trans Graph 22(3):954–961

    Article  Google Scholar 

  15. Kleiman Y, Ovsjanikov M (2019) Robust structure-based shape correspondence. Comput Graphics Forum 38:7–20

    Article  Google Scholar 

  16. Le BH, Deng Z (2014) Robust and accurate skeletal rigging from mesh sequences. ACM Trans Graph 33(4):1–10

    Article  Google Scholar 

  17. Liang J, Lai R, Wong TW, Zhao H (2012) Geometric understanding of point clouds using Laplace-Beltrami operator. In IEEE Conf Comput Vis Pattern Recognit pp 214–221

  18. Mei J, Zhang L, Wu S, Zhen W, Liang Z (2017) 3D tree modeling from incomplete point clouds via optimization and \(\ell _1\)-MST. Int J Geogr Inf Sci 31(5):999–1021

  19. Moon G, Chang J, Lee K (2019) Camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. International Conference on Computer Vision pp 10132–10141

  20. Pang Z, Yong Z, Xiao C (2015) Effective skeletons extraction for animated surfaces based on geometry propagation. Comput Anim Virtual Worlds 26(3–4):301–309

    Article  Google Scholar 

  21. Pantuwong N, Sugimoto M (2012) A novel template-based automatic rigging algorithm for articulated-character animation. Comput Anim Virtual Worlds 23(2):125–141

    Article  Google Scholar 

  22. Qi S, Wang W, Jia B, Shen J, Zhu S (2018) Learning human-object interactions by graph parsing neural networks. European Conference on Computer Vision pp 407–423

  23. Sharf A, Lewiner T, Shamir A, Kobbelt L (2010) On-the-fly curve-skeleton computation for 3D shapes. Comput Graphics Forum 26(3):323–328

    Article  Google Scholar 

  24. Shen W, Bai X, Yang X, Latecki L (2013) Skeleton pruning as trade-off between skeleton simplicity and reconstruction error. Sci China Inf Sci 56(4):1–14

    Article  Google Scholar 

  25. Singh G, Mémoli F, Carlsson G (2007) Topological methods for the analysis of high dimensional data sets and 3D object recognition. Eurographics Symposium on Point-Based Graphics pp 91–100

  26. Snavely N, Seitz F, Szeliski R (2008) Modeling the world from internet photo collections. Int J Comput Vis 80(2):189–210

    Article  Google Scholar 

  27. Sun J, Ovsjanikov M, Guibas L (2009) A concise and provably informative multi-scale signature based on heat diffusion. Comput Graph Forum pp 1383–1392

  28. Tagliasacchi A, Zhang H, Cohen-Or D (2009) Curve skeleton extraction from incomplete point cloud. ACM Trans Graph 28(3):1–9

    Article  Google Scholar 

  29. Tagliasacchi A, Alhashim I, Olson M, Hao Z (2012) Mean curvature skeletons. Comput Graphics Forum 31(5):1735–1744

    Article  Google Scholar 

  30. Wandt B, Rosenhahn B (2019) RepNet: weakly supervised training of an adversarial reprojection network for 3D human pose estimation. Comput Vis Pattern Recognit pp 7782–7791

  31. Wang K, Razzaq A, Wu Z, Feng T, Ali S, Jia T, Wang X, Zhou M (2015) Novel correspondence-based approach for consistent human skeleton extraction. Multimed Tools Appl 75(19):1–22

    Google Scholar 

  32. Wang W, Xu Y, Shen J, Zhu S (2018) Attentive fashion grammar network for fashion landmark detection and clothing category classification. Comput Vis Pattern Recognit pp 4271–4280

  33. Wang W, Zhang Z, Qi S, Shen J, Pang Y, Shao L (2019) Learning compositional neural information fusion for human parsing. International Conference on Computer Vision pp 5702–5712

  34. Wang W, Zhu H, Dai J, Pang Y, Shen J, Shao L (2020) Hierarchical human parsing with typed part-relation reasoning. Comput Vis Pattern Recognit pp 8926–8936

  35. Zheng Q, Sharf A, Tagliasacchi A, Chen B, Zhang H, Sheffer A, Cohen-Or D (2010) Consensus skeleton for non-rigid space-time registration. Comput Graphics Forum 29(2):635–644

    Article  Google Scholar 

  36. Zhang D, Liang S, Zhang C, Jia J (2015) 3D tree skeleton reconstruction based on enhanced pyrlk optical flow algorithm. Journal of Computer-Aided Design and Computer Graphics 27(7):1247–1254

    Google Scholar 

  37. Zhang Y, Shen B, Wang S, Kong D, Yin B (2018) L0-regularization-based skeleton optimization from consecutive point sets of kinetic human body. ISPRS J Photogramm Remote Sens. pp 124–133

  38. Zhou T, Wang W, Qi S, Ling H, Shen J (2020) Cascaded human-object interaction recognition. Comput Vis Pattern Recognit pp 4262–4271

  39. Zimovnov A, Mestetskiy L (2015) Curve-skeleton extraction from visual hull. In International Conference on Computer Vision Theory and Applications pp 666–671

Download references

Acknowledgements

This work was ed in part by the National Natural Science Foundation of China under Grant 62072015, U19B2039, U1811463, 61876012, and in part by the Natural Science Foundation of Beijing under Grant 4202003.

Author information

Authors and Affiliations

  1. Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, 100124, Beijing, China

    Yong Zhang, Lufei Chen, Fei Tan, Shaofan Wang & Baocai Yin

Authors
  1. Yong Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lufei Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fei Tan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shaofan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Baocai Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shaofan Wang.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, Y., Chen, L., Tan, F. et al. An improved \(\ell _1\) median model for extracting 3D human body curve-skeleton. Multimed Tools Appl 80, 33547–33571 (2021). https://doi.org/10.1007/s11042-021-11373-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-021-11373-2

Keywords

Search

Navigation