Data-Efficient Inference of Neural Fluid Fields via SciML Foundation Model

TL;DR

This paper demonstrates that SciML foundation models can greatly reduce data needs and improve the accuracy of inferring real-world 3D fluid dynamics, leveraging pretrained physics knowledge.

Contribution

It introduces a novel collaborative training strategy that integrates SciML foundation models into neural fluid field inference, enhancing generalization and reducing data requirements.

Findings

Achieves 9-36% improvement in PSNR for future prediction.

Reduces training frames by 25-50%.

Outperforms prior approaches in both quantitative and visual metrics.

Abstract

Recent developments in 3D vision have enabled significant progress in inferring neural fluid fields and realistic rendering of fluid dynamics. However, these methods require dense captures of real-world flows, which demand specialized laboratory setups, making the process costly and challenging. Scientific machine learning (SciML) foundation models, pretrained on extensive simulations of partial differential equations (PDEs), encode rich multiphysics knowledge and thus provide promising sources of domain priors for fluid field inference. Nevertheless, the transferability of these foundation models to real-world vision problems remains largely underexplored. In this work, we demonstrate that SciML foundation models can significantly reduce the data requirements for inferring real-world 3D fluid dynamics while improving generalization. Our method leverages the strong forecasting capabilities and meaningful representations learned by SciML foundation models. We introduce a novel collaborative training strategy that equips neural fluid fields with augmented frames and fluid features extracted from the foundation model. Extensive experiments show substantial improvements in both quantitative metrics and visual quality over prior approaches. In particular, our method achieves a 9-36% improvement in peak signal-to-noise ratio (PSNR) for future prediction while reducing the number of required training frames by 25-50%. These results highlight the practical applicability of SciML foundation models for real-world fluid dynamics reconstruction. Our code is available at: https://github.com/delta-lab-ai/SciML-HY.