This Article 
 Bibliographic References 
 Add to: 
Efficient Simplicial Reconstructions of Manifolds from Their Samples
October 2002 (vol. 24 no. 10)
pp. 1349-1357

Abstract—A new algorithm for manifold learning is presented. Given only samples of a finite-dimensional differentiable manifold and no a priori knowledge of the manifold's geometry or topology except for its dimension, the goal is to find a description of the manifold. The learned manifold must approximate the true manifold well, both geometrically and topologically, when the sampling density is sufficiently high. The proposed algorithm constructs a simplicial complex based on approximations to the tangent bundle of the manifold. An important property of the algorithm is that its complexity depends on the dimension of the manifold, rather than that of the embedding space. Successful examples are presented in the cases of learning curves in the plane, curves in space, and surfaces in space; in addition, a case when the algorithm fails is analyzed.

[1] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active Contour Models,” Proc. First IEEE Int'l Conf. Computer Vision, June 1987.
[2] M. Isard and A. Blake, “Condensation-Conditional Density Propagation for Visual Tracking,” Int'l J. Computer Vision, vol. 29, pp. 5-28, 1998.
[3] M. Isard and A. Blake, “ICONDENSATION: Unifying Low-Level and High-Level Tracking in a Stochastic Framework,” Proc. Fifth European Conf. Computer Vision, pp. 893-908, 1998.
[4] D. Freedman and M.S. Brandstein, Provably Fast Algorithms for Contour Tracking Proc. Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 139-144, 2000.
[5] N. Amenta and M. Bern, “Surface Reconstruction by Voronoi Filtering,” Discrete and Computational Geometry, vol. 22, pp. 481-504, 1999.
[6] N. Amenta, M. Bern, and D. Eppstein, “The Crust and the Beta-Skeleton: Combinatorial Curve Reconstruction,” Graphical Models and Image Processing, vol. 60, no. 2, pp. 125-135, 1998.
[7] S. Haykin, Adaptive Filter Theory. Upper Saddle River, NJ: Prentice Hall, 1996.
[8] H. Hoppe, T. DeRose, T. Duchamp, J. McDonald, and W. Stuetzle, “Surface Reconstruction from Unorganized Points,” Proc. SIGGRAPH '92, pp. 71-78, 1992.
[9] H. Hoppe, T. DeRose, T. Duchamp, M. Halstead, H. Jin, J. McDonald, J. Schweitzer, and W. Stuetzle, “Piecewise Smooth Surface Reconstruction,” Proc., ACM SIGGRAPH, pp. 295-302, July 1994.
[10] B. Curless and M. Levoy, “A Volumetric Method for Building Complex Models from Range Images,” Proc. SIGGRAPH '96, pp. 303-312, 1996.
[11] C. Bregler and S.M. Omohundro, “Nonlinear Manifold Learning for Visual Speech Recognition,” Proc. Int'l Conf. Computer Vision, pp. 494-499, 1995.
[12] N. Amenta, M. Bern, and M. Kamvysselis, “A New Voronoi-Based Surface Reconstruction Algorithm,” Proc. SIGGRAPH '98, pp. 415-421, 1998.
[13] N. Amenta and S. Choi, “One-Pass Delaunay Filtering for Homeomorphic 3D Surface reconstruction,” Technical Report TR99-08, Univ. of Texas at Austin, 1999.
[14] T. Dey, K. Melhorn, and E. Ramos, “Curve Reconstruction: Connecting Dots with Good Reason,” Proc. 15th Symp. Computational Geometry, pp. 197-206, 1999.
[15] T. Dey and P. Kumar, “A Simple Provable Algorithm for Curve Reconstruction,” Proc. ACM-SIAM Symp. Discrete Algorithms '99, pp. 893-894, 1999.
[16] S. Cheng and T. Dey, “Improved Construction of Delaunay Based Contour Surfaces,” Proc. ACM Symp. Solid Modeling and Applications, pp. 322-323, 1999.
[17] E. Althaus and K. Melhorn, “TSP-Based Curve Reconstruction in Polynomial Time,” Proc. ACM-SIAM Symp. Discrete Algorithms '00, pp. 686-695, 2000.
[18] T. Dey and R. Wenger, “Reconstructing Curves with Sharp Corners,” Proc. 16th Symp. Computational Geometry, pp. 233-241, 2000.
[19] T. Dey and J. Giesen, “Detecting Undersampling in Surface Reconstruction,” Proc. 17th Symp. Computational Geometry, pp. 257-263, 2001.
[20] C. Gold and J. Snoeyink, “A One Step Crust and Skeleton Extraction Algorithm,” Algorithmica, vol. 30, no. 2, pp. 144-163, 2001.
[21] K. Mulmuley, Computational Geometry: An Introduction through Randomized Algorithms. Englewood Cliffs, N.J.: Prentice Hall, 1994.

Index Terms:
Machine learning, differentiable manifold, simplicial complex.
Daniel Freedman, "Efficient Simplicial Reconstructions of Manifolds from Their Samples," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 10, pp. 1349-1357, Oct. 2002, doi:10.1109/TPAMI.2002.1039206
Usage of this product signifies your acceptance of the Terms of Use.