arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.03311cs.LGcs.AI
收藏

关于标量与向量数据球谐表示的不变性、等变性、相关性与卷积

On Invariance, Equivariance, Correlation and Convolution of Spherical Harmonic Representations for Scalar and Vectorial Data

Offenburg University(奥芬堡大学);Institute for Machine Learning and Analytics(机器学习与分析研究所);Fraunhofer ITWM(弗劳恩霍夫工业数学研究所)

Janis Keuper

AI总结:

本文系统介绍了球谐表示的理论与实现,涵盖旋转不变与等变特征、卷积及精确相关性,并将其推广到向量谐波以处理球面三维向量场。

摘要:

球谐(Spherical Harmonic, SH)域中数据的数学表示近年来在机器学习社区重新引起了越来越多的关注。本技术报告深入介绍了SH表示的理论基础与实际实现,总结了关于旋转不变特征和等变特征,以及球面上信号的卷积和精确相关性的工作。在此基础上,这些方法进一步从标量SH表示推广到向量谐波(Vectorial Harmonics, VH),为球面上的三维向量场提供了相同的能力。

英文摘要:

The mathematical representations of data in the Spherical Harmonic (SH) domain has recently regained increasing interest in the machine learning community. This technical report gives an in-depth introduction to the theoretical foundation and practical implementation of SH representations, summarizing works on rotation invariant and equivariant features, as well as convolutions and exact correlations of signals on spheres. In extension, these methods are then generalized from scalar SH representations to Vectorial Harmonics (VH), providing the same capabilities for 3d vector fields on spheres

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。

↑