Advertisement

Generalized Connectivity Constraints for Spatio-temporal 3D Reconstruction

  • Martin Ralf Oswald
  • Jan Stühmer
  • Daniel Cremers
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8692)

Abstract

This paper introduces connectivity preserving constraints into spatio-temporal multi-view reconstruction. We efficiently model connectivity constraints by precomputing a geodesic shortest path tree on the occupancy likelihood. Connectivity of the final occupancy labeling is ensured with a set of linear constraints on the labeling function. In order to generalize the connectivity constraints from objects with genus 0 to an arbitrary genus, we detect loops by analyzing the visual hull of the scene. A modification of the constraints ensures connectivity in the presence of loops. The proposed efficient implementation adds little runtime and memory overhead to the reconstruction method. Several experiments show significant improvement over state-of-the-art methods and validate the practical use of this approach in scenes with fine structured details.

Keywords

connectivity constraints spatio-temporal 3D reconstruction 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aganj, E., Pons, J.P., Ségonne, F., Keriven, R.: Spatio-temporal shape from silhouette using four-dimensional delaunay meshing. In: ICCV, pp. 1–8 (2007)Google Scholar
  2. 2.
    Ambrosio, L., Fusco, N., Pallara, D.: Functions of bounded variation and free discontinuity problems. Oxford Mathematical Monographs. The Clarendon Press Oxford University Press, New York (2000)zbMATHGoogle Scholar
  3. 3.
    Bleyer, M., Rother, C., Kohli, P., Scharstein, D., Sinha, S.: Object stereojoint stereo matching and object segmentation. In: CVPR, pp. 3081–3088. IEEE (2011)Google Scholar
  4. 4.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE TPAMI 23(11), 1222–1239 (2001)CrossRefGoogle Scholar
  5. 5.
    Chen, C., Freedman, D., Lampert, C.H.: Enforcing topological constraints in random field image segmentation. In: CVPR, pp. 2089–2096 (2011)Google Scholar
  6. 6.
    Cremers, D., Kolev, K.: Multiview stereo and silhouette consistency via convex functionals over convex domains. IEEE TPAMI 33, 1161–1174 (2011)CrossRefGoogle Scholar
  7. 7.
    Dey, T.K., Fan, F., Wang, Y.: An efficient computation of handle and tunnel loops via reeb graphs. ACM Trans. Graph. 32(4), 32 (2013)CrossRefGoogle Scholar
  8. 8.
    Dey, T.K., Li, K., Sun, J., Cohen-Steiner, D.: Computing geometry-aware handle and tunnel loops in 3d models. ACM Trans. Graph. 27(3) (2008)Google Scholar
  9. 9.
    Esteban, C.H., Schmitt, F.: Silhouette and stereo fusion for 3d object modeling. CVIU 96(3), 367–392 (2004)Google Scholar
  10. 10.
    Furukawa, Y., Ponce, J.: Accurate, dense, and robust multiview stereopsis. IEEE TPAMI 32(8), 1362–1376 (2010), http://dx.doi.org/10.1109/TPAMI.2009.161 CrossRefGoogle Scholar
  11. 11.
    Goldluecke, B., Ihrke, I., Linz, C., Magnor, M.: Weighted minimal hypersurface reconstruction. IEEE TPAMI 29(7), 1194–1208 (2007)CrossRefGoogle Scholar
  12. 12.
    Goldluecke, B., Magnor, M.: Space-time isosurface evolution for temporally coherent 3D reconstruction. In: CVPR, vol. I, pp. 350–355 (July 2004)Google Scholar
  13. 13.
    Guillemaut, J.Y., Hilton, A.: Space-time joint multi-layer segmentation and depth estimation. In: 3DIMPVT, pp. 440–447 (2012)Google Scholar
  14. 14.
    Gulshan, V., Rother, C., Criminisi, A., Blake, A., Zisserman, A.: Geodesic star convexity for interactive image segmentation. In: CVPR, pp. 3129–3136. IEEE (2010)Google Scholar
  15. 15.
    Han, X., Xu, C., Prince, J.L.: A topology preserving level set method for geometric deformable models. IEEE TPAMI 25(6), 755–768 (2003)CrossRefGoogle Scholar
  16. 16.
    Institut national de recherche en informatique et en automatique (INRIA) Rhône Alpes: 4d repository, http://4drepository.inrialpes.fr/
  17. 17.
    Jancosek, M., Pajdla, T.: Multi-view reconstruction preserving weakly-supported surfaces. In: CVPR, pp. 3121–3128 (2011)Google Scholar
  18. 18.
    Kazhdan, M.M., Bolitho, M., Hoppe, H.: Poisson surface reconstruction. In: Symposium on Geometry Processing, pp. 61–70 (2006)Google Scholar
  19. 19.
    Kolev, K., Klodt, M., Brox, T., Cremers, D.: Continuous global optimization in multiview 3d reconstruction. IJCV 84(1), 80–96 (2009)CrossRefGoogle Scholar
  20. 20.
    Lorensen, W.E., Cline, H.E.: Marching cubes: A high resolution 3d surface construction algorithm. SIGGRAPH Comput. Graph. 21, 163–169 (1987)CrossRefGoogle Scholar
  21. 21.
    Nowozin, S., Lampert, C.H.: Global connectivity potentials for random field models. In: CVPR, pp. 818–825. IEEE (2009)Google Scholar
  22. 22.
    Oswald, M.R., Cremers, D.: A convex relaxation approach to space time multi-view 3d reconstruction. In: ICCV - Workshop on Dynamic Shape Capture and Analysis (4DMOD) (2013)Google Scholar
  23. 23.
    Pock, T., Chambolle, A.: Diagonal preconditioning for first order primal-dual algorithms in convex optimization. In: ICCV, Washington, DC, USA, pp. 1762–1769 (2011)Google Scholar
  24. 24.
    Starck, J., Hilton, A.: Surface capture for performance-based animation. IEEE Computer Graphics and Applications 27(3), 21–31 (2007)CrossRefGoogle Scholar
  25. 25.
    Stühmer, J., Schröder, P., Cremers, D.: Tree shape priors with connectivity constraints using convex relaxation on general graphs. In: ICCV, Sydney, Australia (December 2013)Google Scholar
  26. 26.
    Vicente, S., Kolmogorov, V., Rother, C.: Graph cut based image segmentation with connectivity priors. In: CVPR (2008)Google Scholar
  27. 27.
    Zeng, Y., Samaras, D., Chen, W., Peng, Q.: Topology cuts: A novel min-cut/max-flow algorithm for topology preserving segmentation in n–d images. Computer Vision and Image Understanding 112(1), 81–90 (2008)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Martin Ralf Oswald
    • 1
  • Jan Stühmer
    • 1
  • Daniel Cremers
    • 1
  1. 1.Department of Computer ScienceTechnische Universität MünchenGarchingGermany

Personalised recommendations