arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.08336cs.LGcs.AIcs.CV
收藏

面向机器学习的3D数据图表示

Graph representations of 3D data for machine learning

Tomasz Prytuła

AI总结:

该研究从机器学习适配性视角综述3D数据的组合表示方法,分析各类表示的优劣,介绍表示生成与切换方法及两个实际应用,兼顾理论性与现实问题导向。

摘要:

本文从机器学习算法可分析性的角度,概述了图、网格等表示3D数据的组合方法。文章梳理了各类表示方法的优缺点,讨论了若干生成不同表示或在其间切换的方法,最后介绍了生命科学与工业领域的两个具体应用。尽管讨论偏理论性,但整体由现实挑战驱动,且更关注实际问题。

英文摘要:

We give an overview of combinatorial methods to represent 3D data, such as graphs and meshes, from the viewpoint of their amenability to analysis using machine learning algorithms. We highlight pros and cons of various representations and we discuss some methods of generating/switching between the representations. We finally present two concrete applications in life science and industry. Despite its theoretical nature, our discussion is in general motivated by, and biased towards real-world challenges.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑