用可迁移神经场加速科学信号跨时间和集合的快速建模。
Fast Amortized Fitting of Scientific Signals Across Time and Ensembles via Transferable Neural Fields
- 通过可迁移特征实现神经场在时序与多组实验间的快速适配。
- 重建精度提升显著，迭代次数减少一个数量级，早期重建质量增益超10 dB。
- 适合需要高效模拟复杂物理系统的研究者，如流体与天体物理领域。
神经场（即隐式神经表示，INRs）在建模连续几何方面具有强大能力，但在高维科学场景中受限于收敛慢和扩展性差。本文将INR模型拓展至处理时空与多变量信号，并展示如何在科学信号间迁移特征，实现时间与集合运行中高效的、可摊销的表示。在受控变换场景（如几何变换与局部扰动）及高保真科学领域（包括湍流、流固撞击动力学和天体物理系统）中，可迁移特征不仅提升了信号保真度，还提高了密度梯度、涡度等导出物理量的准确性。具体而言，该方法使达到目标重建质量所需的迭代次数减少一个数量级，早期重建质量提升多个dB（某些情况超过10 dB），且始终改善基于梯度的物理精度。
原文摘要 · Abstract (English)
Neural fields, also known as implicit neural representations (INRs), offer a powerful framework for modeling continuous geometry, but their effectiveness in high-dimensional scientific settings is limited by slow convergence and scaling challenges. In this study, we extend INR models to handle spatiotemporal and multivariate signals and show how INR features can be transferred across scientific signals to enable efficient and scalable representation across time and ensemble runs in an amortized fashion. Across controlled transformation regimes (e.g., geometric transformations and localized perturbations of synthetic fields) and high-fidelity scientific domains-including turbulent flows, fluid-material impact dynamics, and astrophysical systems-we show that transferable features improve not only signal fidelity but also the accuracy of derived geometric and physical quantities, including density gradients and vorticity. In particular, transferable features reduce iterations to reach target reconstruction quality by up to an order of magnitude, increase early-stage reconstruction quality by multiple dB (with gains exceeding 10 dB in some cases), and consistently improve gradient-based physical accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。