Article
Full entry | Fulltext not available
(moving wall
24 months)
Feedback
Keywords:
information geometry; point cloud; Gaussian mixture model; statistical manifold; divergence; computational geometry
information geometry; point cloud; Gaussian mixture model; statistical manifold; divergence; computational geometry
Summary:
We represent the point clouds of objects and audio signals as manifolds of Gaussian Mixture Models, and analyze the shape variation and compare the audio patterns using three divergence measures, namely the Kullback-Leibler Divergence, Jensen-Shannon Divergence, and Modified Symmetric Kullback-Leibler Divergence. Experiments are conducted on basic geometric shapes, 3D human body shapes, animal shapes, point clouds of the same object produced from the dense point clouds in the PU-GAN (Point Cloud Upsampling Adversarial Network) dataset. Then, we present a method to generate a point cloud of an audio signal using the Short-Time Fourier Transform. The audio-derived point clouds represent frequency, time, and magnitude relationships, enabling analysis of speech and audio patterns. The results across all datasets show that the Modified Symmetric Kullback-Leibler Divergence provides the most distinct and stable comparison between different point clouds, demonstrating its robustness for point cloud comparison.
References:
[1] Amari, S.: Information Geometry and Its Applications. Applied Mathematical Sciences 194. Springer, Tokyo (2016). DOI 10.1007/978-4-431-55978-8 | MR 3495836 | Zbl 1350.94001
[2] Amari, S., Nagaoka, H.: Methods of Information Geometry. Translations of Mathematical Monographs 191. AMS, Providence (2000). DOI 10.1090/mmono/191 | MR 1800071 | Zbl 0960.62005
[3] Amarú, L., Gaillardon, P.-E., Micheli, G. De: EPFL: G-PCD Geometry Point Cloud Dataset. Available at https://www.epfl.ch/labs/mmspg/downloads/geometry-point-cloud-dataset
[4] Broniatowski, M., Stummer, W.: A precise bare simulation approach to the minimization of some distances. I. Foundations. IEEE Trans. Inf. Theory 69 (2023), 3062-3120. DOI 10.1109/TIT.2022.3215496 | MR 4581281 | Zbl 1542.94034
[5] Ge, B., Najar, F., Bouguila, N.: Data-weighted multivariate generalized Gaussian mixture model: Application to point cloud robust registration. J. Imaging 9 (2023), Article ID 179, 17 pages. DOI 10.3390/jimaging9090179
[6] Ghojogh, B., Nekoei, H., Ghojogh, A., Karray, F., Crowley, M.: Sampling algorithms, from survey sampling to Monte Carlo methods: Tutorial and literature review. Available at https://arxiv.org/abs/2011.00901 (2020), 25 pages. DOI 10.48550/arXiv.2011.00901
[7] Goel, K., Michael, N., Tabib, W.: Probabilistic point cloud modeling via self-organizing Gaussian mixture models. IEEE Robotics Automat. Lett. 8 (2023), 2526-2533. DOI 10.1109/LRA.2023.3256923
[8] Harsha, K. V., Moosath, K. S. S.: $F$-geometry and Amari's $\alpha$-geometry on a statistical manifold. Entropy 16 (2014), 2472-2487. DOI 10.3390/e16052472
[9] Hausdorff, F.: Felix Hausdorff -- gesammelte Werke. Band III: Mengenlehre. Springer, Berlin (2008), German. DOI 10.1007/978-3-540-76807-4 | MR 2478457 | Zbl 1149.01022
[10] Hirose, O.: Geodesic-based Bayesian coherent point drift. IEEE Trans. Pattern Anal. Machine Intelligence 45 (2023), 5816-5832. DOI 10.1109/TPAMI.2022.3214191
[11] Hoyos-Osorio, J. K., Sanchez-Giraldo, L. G.: The representation Jensen-Shannon divergence. Available at https://arxiv.org/abs/2305.16446 (2024), 30 pages. DOI 10.48550/arXiv.2305.16446
[12] Jannah, W., Saputro, D. R. S.: Parameter estimation of Gaussian mixture models (GMM) with expectation maximization (EM) algorithm. AIP Conf. Proc. 2566 (2022), Article ID 04002. DOI 10.1063/5.0117119
[13] Kullback, S., Leibler, R. A.: On information and sufficiency. Ann. Math. Stat. 22 (1951), 79-86. DOI 10.1214/aoms/1177729694 | MR 0039968 | Zbl 0042.38403
[14] Lee, Y., Kim, S., Choi, J., Park, F.: A statistical manifold framework for point cloud data. Proceedings of the 39th International Conference on Machine Learning PMLR, Cambridge (2022), 12378-12402.
[15] Leiber, M., Marnissi, Y., Barrau, A., Badaoui, M. El: Differentiable short-time Fourier transform with respect to the Hop length. Available at https://arxiv.org/abs/2308.02421 (2023), 8 pages. DOI 10.48550/arXiv.2308.02421
[16] Li, R., Li, X., Fu, C.-W., Cohen-Or, D., Heng, P.-A.: PU-GAN: A point cloud upsampling adversarial network. 2019 IEEE/CVF International Conference on Computer Vision (ICCV) IEEE, Los Alamitos (2019), 7203-7212. DOI 10.1109/ICCV.2019.00730
[17] Li, Y., Xie, S., Wan, Z., Lv, H., Song, H., Lv, Z.: Graph-powered learning methods in the internet of things: A survey. Machine Learning Appl. 11 (2023), Article ID 100441, 15 pages. DOI 10.1016/j.mlwa.2022.100441
[18] Liese, F., Vajda, I.: On divergences and informations in statistics and information theory. IEEE Trans. Inf. Theory 52 (2006), 4394-4412. DOI 10.1109/TIT.2006.881731 | MR 2300826 | Zbl 1287.94025
[19] Lin, J.: Divergence measures based on the Shannon entropy. IEEE Trans. Inf. Theory 37 (1991), 145-151. DOI 10.1109/18.61115 | MR 1087893 | Zbl 0712.94004
[20] Mahalanobis, P. C.: Reprint of: Mahalanobis, P. C. (1936) ``On the generalised distance in statistics''. S\=ankhya, Ser. A 80 (2018), 1-7. DOI 10.1007/s13171-019-00164-5 | MR 3968355 | Zbl 1477.62001
[21] Moenning, C., Dodgson, N. A.: Fast Marching Farthest Point Sampling. Technical Report 562. University of Cambridge, Computer Laboratory, Cambridge (2003).
[22] MPI-FAUST dataset. Available at https://faust-leaderboard.is.tuebingen.mpg.de/
[23] Nielsen, F.: An elementary introduction to information geometry. Entropy 22 (2020), Article ID 1100, 61 pages. DOI 10.3390/e22101100
[24] Osgood, B.: Lecture notes for EE 261: The Fourier transform and its applications. Available at https://see.stanford.edu/materials/lsoftaee261/book-fall-07.pdf
[25] Peng, C.-C.: Depth camera point cloud sharpening. International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) IEEE, Los Alamitos (2023), 719-720. DOI 10.1109/ICCE-Taiwan58799.2023.10226686
[26] Rubner, Y., Tomasi, C., Guibas, L. J.: The earth mover's distance as a metric for image retrieval. Int. J. Comput. Vis. 40 (2000), 99-121. DOI 10.1023/A:1026543900054 | Zbl 1012.68705
[27] Saranti, A., Pfeifer, B., Gollob, C., Stampfer, K., Holzinger, A.: From 3D point-cloud data to explainable geometric deep learning: State-of-the-art and future challenges. WIREs Data Mining Knowledge Disc. 14 (2024), Article ID e1554, 45 pages. DOI 10.1002/widm.1554
[28] Stern, R. M.: Short-time Fourier analysis. Advanced Digital Signal Processing Course Notes Carnegie Mellon University, Pittsburgh (2022), 35-52 Available at \let \relax \brokenlink{ http:{//course.ece.cmu.edu/ ece491/lectures/L25/STFT_Notes_ADSP.pdf}}.
[29] Vishwakarma, A., Moosath, K. S. S.: Information geometric framework for point cloud data. Available at https://arxiv.org/abs/2405.04864 (2024), 13 pages. DOI 10.48550/arXiv.2405.04864
[30] Wang, R., Law, A. C., Garcia, D., Yang, S., Kong, Z.: Development of structured light 3D-scanner with high spatial resolution and its applications for additive manufacturing quality assurance. Int. J. Adv. Manufac. Technol. 117 (2021), 845-862. DOI 10.1007/s00170-021-07780-2
[31] Yang, Y., Feng, C., Shen, Y., Tian, D.: FoldingNet: Point cloud auto-encoder via deep grid deformation. IEEE/CVF Conference on Computer Vision and Pattern Recognition 2018 IEEE, Los Alamitos (2018), 206-215. DOI 10.1109/CVPR.2018.00029
[32] Zyrianov, V., Zhu, X., Wang, S.: Learning to generate realistic LiDAR point clouds. Available at https://arxiv.org/abs/2209.03954 (2022), 27 pages. DOI 10.48550/arXiv.2209.03954
Search
Partner of
