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 2404.17620cs.LGcs.CVcs.GR
收藏

Neural Modes:非线性模态子空间的自监督学习

Neural Modes: Self-supervised Learning of Nonlinear Modal Subspaces

ETH Zürich(苏黎世联邦理工学院)

Jiahong Wang, Yinwei Du, Stelian Coros, Bernhard Thomaszewski

AI总结:

提出一种自监督方法,通过在训练中直接最小化系统机械能来学习基于物理的子空间,解决了现有方法高能量、潜在空间纠缠及泛化差的问题,获得了反映物理平衡且具可解释性的子空间。

摘要:

我们提出了一种自监督方法,用于学习面向实时仿真的基于物理的子空间。现有的基于学习的方法通过以纯几何方式近似预定义的仿真数据来构建子空间。然而,这种方法倾向于产生高能量构型,导致潜在空间维度纠缠,并且在训练集之外泛化能力差。为了克服这些限制,我们提出了一种在训练期间直接最小化系统机械能的自监督方法。我们表明,我们的方法所学习到的子空间能够反映物理平衡约束,解决了先前方法的过拟合问题,并提供了可解释的潜在空间参数。

英文摘要:

We propose a self-supervised approach for learning physics-based subspaces for real-time simulation. Existing learning-based methods construct subspaces by approximating pre-defined simulation data in a purely geometric way. However, this approach tends to produce high-energy configurations, leads to entangled latent space dimensions, and generalizes poorly beyond the training set. To overcome these limitations, we propose a self-supervised approach that directly minimizes the system's mechanical energy during training. We show that our method leads to learned subspaces that reflect physical equilibrium constraints, resolve overfitting issues of previous methods, and offer interpretable latent space parameters.

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。

↑