arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.05965cs.LGeess.SP
收藏

球面数据的混合神经表示

Hybrid Neural Representations for Spherical Data

Pohang University of Science and Technology(浦项科技大学)

Hyomin Kim, Yunhui Jang, Jaeho Lee, Sungsoo Ahn

AI总结:

本文提出球面数据混合神经表示(HNeR-S),结合球面特征网格与多层感知机,有效捕捉天气及CMB数据中的非线性细节,并在回归、超分辨率、时间插值和压缩任务中验证其有效性。

摘要:

在本文中,我们研究了球面数据的混合神经表示,这是一个在科学研究中日益相关的领域。特别是,我们的工作聚焦于天气和气候数据以及宇宙微波背景(CMB)数据。尽管以往的研究已经深入探讨了基于坐标的球面信号神经表示,但它们往往无法捕捉高度非线性信号的复杂细节。为了解决这一局限性,我们提出了一种名为球面数据混合神经表示(HNeR-S)的新方法。我们的主要思想是使用球面特征网格来获取位置特征,并将其与多层感知机相结合以预测目标信号。我们考虑了分别与天气数据和CMB数据对齐的等距圆柱投影和层次等面积隔离纬度像素化结构的特征网格。我们广泛验证了我们的HNeR-S在回归、超分辨率、时间插值和压缩任务中的有效性。

英文摘要:

In this paper, we study hybrid neural representations for spherical data, a domain of increasing relevance in scientific research. In particular, our work focuses on weather and climate data as well as comic microwave background (CMB) data. Although previous studies have delved into coordinate-based neural representations for spherical signals, they often fail to capture the intricate details of highly nonlinear signals. To address this limitation, we introduce a novel approach named Hybrid Neural Representations for Spherical data (HNeR-S). Our main idea is to use spherical feature-grids to obtain positional features which are combined with a multilayer perception to predict the target signal. We consider feature-grids with equirectangular and hierarchical equal area isolatitude pixelization structures that align with weather data and CMB data, respectively. We extensively verify the effectiveness of our HNeR-S for regression, super-resolution, temporal interpolation, and compression tasks.

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。

↑