Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Non-Euclidean Sliced Optimal Transport Sampling (2402.16981v1)

Published 26 Feb 2024 in cs.GR

Abstract: In machine learning and computer graphics, a fundamental task is the approximation of a probability density function through a well-dispersed collection of samples. Providing a formal metric for measuring the distance between probability measures on general spaces, Optimal Transport (OT) emerges as a pivotal theoretical framework within this context. However, the associated computational burden is prohibitive in most real-world scenarios. Leveraging the simple structure of OT in 1D, Sliced Optimal Transport (SOT) has appeared as an efficient alternative to generate samples in Euclidean spaces. This paper pushes the boundaries of SOT utilization in computational geometry problems by extending its application to sample densities residing on more diverse mathematical domains, including the spherical space Sd , the hyperbolic plane Hd , and the real projective plane Pd . Moreover, it ensures the quality of these samples by achieving a blue noise characteristic, regardless of the dimensionality involved. The robustness of our approach is highlighted through its application to various geometry processing tasks, such as the intrinsic blue noise sampling of meshes, as well as the sampling of directions and rotations. These applications collectively underscore the efficacy of our methodology.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (70)
  1. Abikoff W.: The uniformization theorem. The American Mathematical Monthly 88, 8 (1981), 574–592.
  2. Wasserstein generative adversarial networks. In International conference on machine learning (2017), PMLR, pp. 214–223.
  3. Distributed principal component analysis with limited communication. Advances in Neural Information Processing Systems 34 (2021), 2823–2834.
  4. A simple push-pull algorithm for blue-noise sampling. Transactions on Visualization and Computer Graphics 23, 12 (Dec. 2017), 2496–2508.
  5. Alexa M.: Super-fibonacci spirals: Fast, low-discrepancy sampling of so (3). In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022), pp. 8291–8300.
  6. Spherical sliced-wasserstein. arXiv preprint arXiv:2206.08780 (2022).
  7. Bonneel N., Coeurjolly D.: SPOT: Sliced Partial Optimal Transport. ACM Trans. Graph. 38, 4 (July 2019).
  8. Hyperbolic sliced-wasserstein via geodesic and horospherical projections. arXiv preprint arXiv:2211.10066 (2022).
  9. Möbius registration. 211–220.
  10. Bonneel N., Digne J.: A survey of optimal transport for computer graphics and computer vision. 439–460.
  11. Bonnotte N.: Unidimensional and evolution methods for optimal transportation. PhD thesis, Université Paris Sud-Paris XI; Scuola normale superiore (Pise, Italie), 2013.
  12. Boumal N.: An introduction to optimization on smooth manifolds. Cambridge University Press, 2023.
  13. Discrete conformal maps and ideal hyperbolic polyhedra. Geometry & Topology 19, 4 (2015), 2155–2215.
  14. Bridson R.: Fast poisson disk sampling in arbitrary dimensions. SIGGRAPH sketches 10, 1 (2007), 1.
  15. Sliced and radon wasserstein barycenters of measures. Journal of Mathematical Imaging and Vision 51 (2015), 22–45.
  16. Capacity-constrained point distributions: A variant of Lloyd’s method. ACM Trans. Graph. 28, 3 (2009), 86:1–8.
  17. Parallel poisson disk sampling with spectrum analysis on surfaces. ACM Transactions on Graphics 29 (2010).
  18. Optimal transport for domain adaptation. IEEE transactions on pattern analysis and machine intelligence 39, 9 (2016), 1853–1865.
  19. Dart throwing on surfaces. In Computer Graphics Forum (2009), vol. 28, Wiley Online Library, pp. 1217–1226.
  20. Geometric median in nearly linear time. In Proceedings of the forty-eighth annual ACM symposium on Theory of Computing (2016), pp. 9–21.
  21. Cabrelli C. A., Molter U. M.: A linear time algorithm for a matching problem on the circle. Information processing letters 66, 3 (1998), 161–164.
  22. Robust fairing via conformal curvature flow. ACM Transactions on Graphics (TOG) 32, 4 (2013), 1–10.
  23. Blue noise through optimal transport. ACM Trans. Graph. 31, 6 (2012), 171.
  24. Transportation distances on the circle and applications. arXiv preprint arXiv:0906.5499 (2009).
  25. A hyperbolic-to-hyperbolic graph convolutional network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021), pp. 154–163.
  26. On the strategyproofness of the geometric median. In International Conference on Artificial Intelligence and Statistics (2023), PMLR, pp. 2603–2640.
  27. Pot: Python optimal transport. Journal of Machine Learning Research 22, 78 (2021), 1–8.
  28. Fundamentals of spherical parameterization for 3d meshes. In ACM SIGGRAPH 2003 Papers. 2003, pp. 358–363.
  29. A discrete uniformization theorem for polyhedral surfaces. Journal of differential geometry 109, 2 (2018), 223–256.
  30. Discrete conformal equivalence of polyhedral surfaces. ACM Trans. Graph. 40, 4 (2021).
  31. Gu X., Yau S.-T.: Global conformal surface parameterization. In Proceedings of the 2003 Eurographics/ACM SIGGRAPH symposium on Geometry processing (2003), pp. 127–137.
  32. Efficient maximal poisson-disk sampling and remeshing on surfaces. Computers & Graphics 46 (2015), 72–79.
  33. Conformal surface parameterization for texture mapping. IEEE Transactions on Visualization and Computer Graphics 6, 2 (2000), 181–189.
  34. Supervised word mover’s distance. Advances in neural information processing systems 29 (2016).
  35. Statistical analysis and modelling of spatial point patterns. John Wiley & Sons, 2008.
  36. Blue noise sampling using an sph-based method. Transactions on Graphics 34, 6 (2015), 1–11.
  37. Spherical fibonacci mapping. ACM Transactions on Graphics (TOG) 34, 6 (2015), 1–7.
  38. Discrete conformal mappings via circle patterns. ACM Transactions on Graphics (TOG) 25, 2 (2006), 412–438.
  39. Lee J. M.: Riemannian manifolds: an introduction to curvature, vol. 176. Springer Science & Business Media, 2006.
  40. Luo F.: Combinatorial yamabe flow on surfaces. Communications in Contemporary Mathematics 6, 05 (2004), 765–780.
  41. On centroidal voronoi tessellation, energy smoothness and fast computation. Transactions on Graphics 28, 4 (08 2009), 1–17.
  42. On centroidal voronoi tessellation—energy smoothness and fast computation. ACM Transactions on Graphics (ToG) 28, 4 (2009), 1–17.
  43. The discrete geodesic problem. SIAM Journal on Computing 16, 4 (1987), 647–668.
  44. Statistical and topological properties of sliced probability divergences. Advances in Neural Information Processing Systems 33 (2020), 20802–20812.
  45. Nader G., Guennebaud G.: Instant transport maps on 2d grids. ACM Trans. Graph. 37, 6 (2018), 13.
  46. Spectral sampling of manifolds. ACM Transactions on Graphics (TOG) 29, 6 (2010), 1–8.
  47. Sliced optimal transport sampling. ACM Trans. Graph. 39, 4 (2020), 99.
  48. Peyré G., Cohen L. D.: Geodesic remeshing using front propagation. International Journal of Computer Vision 69 (2006), 145–156.
  49. Computational optimal transport: With applications to data science. Foundations and Trends® in Machine Learning 11, 5-6 (2019), 355–607.
  50. Pérard-Gayot A.: BVH construction and traversal library, 2023. URL: https://github.com/madmann91/bvh.
  51. N-dimensional probablility density function transfer and its application to colour transfer. In IEEE Int. Conf. on Computer Vision (ICCV) (2005).
  52. Variance analysis for monte carlo integration. ACM Trans. Graph. (Proc. SIGGRAPH) 34, 4 (2015), 124:1–124:14.
  53. Wasserstein blue noise sampling. ACM Transactions on Graphics (TOG) 36, 5 (2017), 1–13.
  54. Wasserstein barycenter and its application to texture mixing. In International Conference on Scale Space and Variational Methods in Computer Vision (2011), Springer, pp. 435–446.
  55. Inter-surface maps via constant-curvature metrics. ACM Transactions on Graphics (TOG) 39, 4 (2020), 119–1.
  56. Convolutional wasserstein distances: Efficient optimal transportation on geometric domains. ACM Trans. Graph. 34, 4 (2015), Art. 66.
  57. Scalable multi-class sampling via filtered sliced optimal transport. arXiv preprint arXiv:2211.04314 (2022).
  58. Variance and convergence analysis of Monte Carlo line and segment sampling. Computer Graphics Forum (Proceedings of EGSR) 36, 4 (June 2017).
  59. Analysis of sample correlations for monte carlo rendering. 473–491.
  60. Earth mover’s distances on discrete surfaces. ACM Trans. Graph. 33, 4 (2014), Art. 67.
  61. Consistent mesh partitioning and skeletonisation using the shape diameter function. The Visual Computer 24 (2008), 249–259.
  62. Conformal equivalence of triangle meshes. In ACM SIGGRAPH 2008 papers. 2008, pp. 1–11.
  63. Sampling implicit surfaces based on stochastic differential equations with converging constraint. Computers & Graphics 24, 3 (2000), 419–431.
  64. Villani C., et al.: Optimal transport: old and new, vol. 338. Springer, 2009.
  65. Evolutionary morphing. IEEE, 2005.
  66. Weiszfeld E.: Sur le point pour lequel la somme des distances de n points donnés est minimum. Tohoku Mathematical Journal, First Series 43 (1937), 355–386.
  67. Blue noise sampling of surfaces. Computers & Graphics 36, 4 (2012), 232–240.
  68. Centroidal power diagrams with capacity constraints: Computation, applications, and extension. Transactions on Graphics 35, 6 (2016), 1–12.
  69. Yuksel C.: Sample elimination for generating poisson disk sample sets. In Computer Graphics Forum (2015), vol. 34, Wiley Online Library, pp. 25–32.
  70. Particle-based anisotropic surface meshing. Transactions on Graphics 32, 4 (2013), 99–1.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets