Reconstructing 3D Flow from 2D Data with Diffusion Transformer

TL;DR

This paper introduces a Diffusion Transformer model that reconstructs 3D fluid flow fields from 2D data, reducing computational costs and expanding application possibilities in fluid dynamics analysis.

Contribution

The paper presents a novel Diffusion Transformer approach that effectively reconstructs 3D flow from 2D slices, incorporating positional embedding and efficient attention mechanisms.

Findings

Accurately reconstructs 3D flow from 2D data

Reduces computational costs compared to traditional methods

Produces realistic 3D flow simulations

Abstract

Fluid flow is a widely applied physical problem, crucial in various fields. Due to the highly nonlinear and chaotic nature of fluids, analyzing fluid-related problems is exceptionally challenging. Computational fluid dynamics (CFD) is the best tool for this analysis but involves significant computational resources, especially for 3D simulations, which are slow and resource-intensive. In experimental fluid dynamics, PIV cost increases with dimensionality. Reconstructing 3D flow fields from 2D PIV data could reduce costs and expand application scenarios. Here, We propose a Diffusion Transformer-based method for reconstructing 3D flow fields from 2D flow data. By embedding the positional information of 2D planes into the model, we enable the reconstruction of 3D flow fields from any combination of 2D slices, enhancing flexibility. We replace global attention with window and plane attention to reduce computational costs associated with higher dimensions without compromising performance. Our experiments demonstrate that our model can efficiently and accurately reconstruct 3D flow fields from 2D data, producing realistic results.