##plugins.themes.academic_pro.article.main##
Abstract
machine learning methods are increasingly resorted to to solve this issue. If we imagine the work of a machine learning algorithm in the form of a "black box", to which data of a given type is fed to the input and the algorithm outputs a prediction in the form of data of a given type, then if data encoding three-dimensional structures are presented at the input and/or output, we talk about the field of machine learning, which is called 3D ML (three dimensional data machine learning problems) or, the term Geometric deep learning is often found when it comes to the use of deep architectures.
Keywords
often
methods
increasingly
architectures
##plugins.themes.academic_pro.article.details##
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
Beknazarova Saida Safibullayevna, & Anvarxo’jaev Sarvarxo’ja A’zamxo’ja o’g’li. (2022). Representation Forms Of 3d Data- Objects. Texas Journal of Multidisciplinary Studies, 5, 309–311. Retrieved from https://zienjournals.com/index.php/tjm/article/view/904
References
- Russell S. Artificial Intelligence: a Modern Approach, S. Russell, P. Norvig / Williams, Moscow, 2018, 1408 p.
- Novotni, Marcin and Reinhard Klein. “Shape retrieval using 3D Zernike descriptors.” Computer-Aided Design 36 (2004): 1047-1062. [project page]
- Fisher, Matthew & Savva, Manolis & Hanrahan, Pat. (2011). Characterizing Structural Relationships in Scenes Using Graph Kernels. ACM Trans. Graph… 30. 34. 10.1145/2010324.1964929.
- Berjón, Daniel & Morán, Francisco. (2012). Fast human pose estimation using 3D Zernike descriptors. Proceedings of SPIE — The International Society for Optical Engineering. 8290. 19-. 10.1117/12.908963.
- Mescheder, Lars & Oechsle, Michael & Niemeyer, Michael & Nowozin, Sebastian & Geiger, Andreas. (2018). Occupancy Networks: Learning 3D Reconstruction in Function Space. [code]