Skip to main content
SpringerLink
Log in

Mesh segmentation based on curvatures using the GPU

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

Abstract

This paper proposes an efficient algorithm for decomposition of a 3D arbitrary triangular mesh into surface patches. Our method is based on the discrete curvatures for an accurate partitioning criterion and presents a fast clustering scheme of vertices using quick shift algorithm. It was implemented on the GPU (Graphics Processing Unit) because it is common for object geometry to exist in graphic memory so that more computational work is done directly on the graphic device. The proposed method results in fast estimation of curvatures and high quality of mesh segmentation. Also we applied it to NPR drawing of 3D meshes.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Abidi M, Page D, Koschan A (2003) Perception-based 3D triangle mesh segmentation using fast marching watersheds. In: Proc. of Computer Vision and Pattern Recognition 2003

  2. Attene M, Katz S, Mortara M, Patané G, Spagnuolo A , Tal M (2006) Mesh segmentation – a comparative study. In: Proc. of Shape Modeling International 2006

  3. Batagelo H, Wu S-T (2007) Estimating curvatures and their derivatives on meshes of arbitrary topology from sampling directions. Vis Comput 23(9-11):803–812

    Article  Google Scholar 

  4. Chen L, Georganas N (2006) An efficient and robust algorithm for 3D mesh segmentation. Multimed Tools Appl 29(2):109–125

    Article  Google Scholar 

  5. Cohen-Steiner D, Alliez P, Desbrun M (2004) Variational shape approximation. ACM Trans Graph (Proc. of SIGGRAPH 2004) 23(3):905–914

    Article  Google Scholar 

  6. Fulkerson B, Soatto S (2010) Really quick shift: image segmentation on a GPU. In: Proc. of European Conference on Computer Vision 2010

  7. Griffin W, Wang Y, Berrios D, Olano M (2011) GPU curvature estimation on deformable meshes. In: Proc. of Interactive 3D Graphics and Games 2011. to appear

  8. Kaplansky L, Tal A (2009) Mesh segmentation refinement. Comput Graph Forum (Proc. of Pacific Graphics 2009) 28(7):1995–2003

    Article  Google Scholar 

  9. Lavoué G, Dupont F, Baskurt A (2005) A new cad mesh segmentation method, based on curvature tensor analysis. Comput Aided Des 37(10):975–987

    Article  Google Scholar 

  10. Rusinkiewicz S (2004) Estimating curvatures and their derivatives on triangle meshes. In: Proc. of 3D Data Processing, Visualization, and Transmission 2004

  11. Shamir A (2008) A survey on mesh segmentation techniques. Comput Graph Forum 27(6):1539–1556

    Article  MATH  Google Scholar 

  12. Vedaldi A, Soatto S (2008) Quick shift and kernel methods for mode seeking. In: Proc. of European Conference on Computer Vision 2008

  13. Vieira M, Shimada K (2005) Surface mesh segmentation and smooth surface extraction through region growing. Comput Aided Geom Des 22(8):771–791

    Article  MATH  MathSciNet  Google Scholar 

  14. Wu J, Kobbelt L (2005) Structure recovery via hybrid variational surface approximation. Comput Graph Forum (Proc. of Eurographics 2005) 24(3):277–284

    Article  Google Scholar 

  15. Yamauchi H, Gumhold S, Zayer R, Seidel H-P (2005) Mesh segmentation driven by gaussian curvature. Vis Comput (Proc. of Pacific Graphics 2005) 21(8-10):659–668

    Google Scholar 

  16. Yamauchi H, Lee S, Lee Y, Ohtake Y, Belyaev A, Seidel H-P (2005) Feature sensitive mesh segmentation with mean shift. In: Proc. of Shape Modeling International 2005

Download references

Acknowledgments

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology (No. 2011-0015072, NRF-2013R1A1A2011602). This research was supported by Hallym University Research Fund (HRF-201309-019).

Author information

Authors and Affiliations

  1. Department of Information and Communication, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul, 136-701, Korea

    Jung Lee

  2. Department of the Mobile Media, Suwon Women’s University, 62 Suwonyeodae-gil, Gwonseon-gu, Suwon-si, Gyeonggi-do, 441-748, Korea

    Seokhun Kim

  3. Department of Ubiquitous Computing, Hallym University, 1 Hallymdaehak-gil Chuncheon-si, Gangwon-do, 200-702, Korea

    Sun-Jeong Kim

Authors
  1. Jung Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Seokhun Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sun-Jeong Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sun-Jeong Kim.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lee, J., Kim, S. & Kim, SJ. Mesh segmentation based on curvatures using the GPU. Multimed Tools Appl 74, 3401–3412 (2015). https://doi.org/10.1007/s11042-014-2104-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-014-2104-1

Keywords

Search

Navigation