Riemannian Filters for Multi-variate Mesh Signals

Teodor Cioaca, Bogdan Dumitrescu, Mihai Sorin Stupariu

2017

Abstract

Designing filters over irregular non-Euclidean domains requires algorithms that take into account the intrinsic curvature of these domains. We propose a new filtering method based on Riemannian weighted averages. The resulting filters are non-Euclidean adaptations of the mean shift and blurring mean shift algorithms. We also introduce a hybrid, efficient computing strategy by combining these iterative filtering methods with wavelet multi-resolution editing. The applications of our filters include multi-variate mesh data smoothing, denoising, attribute enhancement and curvature filtering.

References

  1. Aftab, K., Hartley, R., and Trumpf, J. (2015). Generalized Weiszfeld algorithms for Lq optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37:728-745.
  2. Caseiro, R., Henriques, J. a. F., Martins, P., and Batista, J. (2012). Semi-intrinsic mean shift on riemannian manifolds. In Proceedings of the 12th European Conference on Computer Vision - Volume Part I, ECCV'12, pages 342-355, Berlin, Heidelberg. Springer-Verlag.
  3. Cerveri, P., Manzotti, A., Marchente, M., Confalonieri, N., and Baroni, G. (2012). Mean-shifted surface curvature algorithm for automatic bone shape segmentation in orthopedic surgery planning: a sensitivity analysis. Computer Aided Surgery, 17(3):128-141. PMID: 22462564.
  4. Cetingul, H. E. and Vidal, R. (2009). Intrinsic mean shift for clustering on stiefel and grassmann manifolds. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 1896-1902.
  5. Cignoni, P., Corsini, M., and Ranzuglia, G. (2008). MeshLab: an Open-Source 3D Mesh Processing System. Ercim News, 2008.
  6. Cioaca, T., Dumitrescu, B., and Stupariu, M.-S. (2016). Graph-based wavelet representation of multi-variate terrain data. Computer Graphics Forum, 35(1):44-58.
  7. Comaniciu, D. and Meer, P. (2002). Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell., 24(5):603-619.
  8. Fletcher, P. T., Venkatasubramanian, S., and Joshi, S. (2008). Robust statistics on riemannian manifolds via the geometric median. In Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, pages 1-8.
  9. Fletcher, P. T., Venkatasubramanian, S., and Joshi, S. (2009). The geometric median on riemannian manifolds with application to robust atlas estimation. NeuroImage, 45(1, Supplement 1):S143 - S152. Mathematics in Brain Imaging.
  10. Fukunaga, K. and Hostetler, L. (1975). The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Transactions on Information Theory, 21(1):32-40.
  11. Hildebrandt, K. and Polthier, K. (2004). Anisotropic Filtering of Non-Linear Surface Features. Computer Graphics Forum, 23:391-400.
  12. Jones, T. R., Durand, F., and Desbrun, M. (2003). Noniterative, feature-preserving mesh smoothing. ACM Trans. Graph., 22(3):943-949.
  13. Lee, K. and Wang, W. (2005). Feature-preserving mesh denoising via bilateral normal filtering. In 9th International Conference on Computer-Aided Design and Computer Graphics, CAD/Graphics 2005, Hong Kong, China, 7-10 December, 2005, page 6.
  14. Melvaer, E. L. and Reimers, M. (2012). Geodesic polar coordinates on polygonal meshes. Computer Graphics Forum, 31(8):2423-2435.
  15. Pennec, X. (2006). Intrinsic statistics on riemannian manifolds: Basic tools for geometric measurements. J. Math. Imaging Vis., 25(1):127-154.
  16. Polthier, K. and Schmies, M. (1998). Straightest Geodesics on Polyhedral Surfaces, pages 135-150. Springer Berlin Heidelberg.
  17. Shamir, A., Shapira, L., and Cohen-Or, D. (2006). Mesh analysis using geodesic mean-shift. Vis. Comput., 22(2):99-108.
  18. Solomon, J., Crane, K., Butscher, A., and Wojtan, C. (2014). A general framework for bilateral and mean shift filtering. ArXiv e-print 1405.4734, 32.
  19. Subbarao, R. and Meer, P. (2009). Nonlinear mean shift over riemannian manifolds. International Journal of Computer Vision, 84(1):1-20.
  20. Taubin, G. (1995). Curve and surface smoothing without shrinkage. In Proceedings of the Fifth International Conference on Computer Vision, ICCV 7895, pages 852-852, Washington, DC, USA. IEEE Computer Society.
  21. Wang, W. and Carreira-Perpin, M. . (2010). Manifold blurring mean shift algorithms for manifold denoising. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pages 1759-1766.
  22. Yamauchi, H., Lee, S., Lee, Y., Ohtake, Y., Belyaev, A., and Seidel, H.-P. (2005). Feature sensitive mesh segmentation with mean shift. In Proceedings of the International Conference on Shape Modeling and Applications 2005, SMI 7805, pages 238-245, Washington, DC, USA. IEEE Computer Society.
  23. Zhang, X., Li, G., Xiong, Y., and He, F. (2008). 3D Mesh Segmentation Using Mean-Shifted Curvature, pages 465-474. Springer Berlin Heidelberg, Berlin, Heidelberg.
  24. Zheng, Y., Fu, H., Au, O. K.-C., and Tai, C.-L. (2011). Bilateral normal filtering for mesh denoising. IEEE Transactions on Visualization and Computer Graphics, 17(10):1521-1530.
Download


Paper Citation


in Harvard Style

Cioaca T., Dumitrescu B. and Stupariu M. (2017). Riemannian Filters for Multi-variate Mesh Signals . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2017) ISBN 978-989-758-224-0, pages 228-235. DOI: 10.5220/0006128602280235


in Bibtex Style

@conference{grapp17,
author={Teodor Cioaca and Bogdan Dumitrescu and Mihai Sorin Stupariu},
title={Riemannian Filters for Multi-variate Mesh Signals},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2017)},
year={2017},
pages={228-235},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006128602280235},
isbn={978-989-758-224-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2017)
TI - Riemannian Filters for Multi-variate Mesh Signals
SN - 978-989-758-224-0
AU - Cioaca T.
AU - Dumitrescu B.
AU - Stupariu M.
PY - 2017
SP - 228
EP - 235
DO - 10.5220/0006128602280235