Diffusion-Based Models for Unpaired Superresolution in Fluid Dynamics
SIAM Journal on Scientific Computing · 31.08.2026 · 48 (4) · C862-C889
DOI: 10.1137/25m1751426 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 28.07.2026. Verfasst von Wuzhe Xu und 4 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Gefördert von: National Science Foundation, Data Science Initiative at the University of Minnesota, Office of Naval Research.
Abstract (Originalsprache)
High-fidelity, high-resolution numerical simulations are crucial for studying complex multiscale phenomena in fluid dynamics, such as turbulent flows and ocean waves. However, direct numerical simulations with high-resolution solvers are computationally prohibitive. As an alternative, superresolution techniques enable the enhancement of low-fidelity, low-resolution simulations. However, traditional superresolution approaches rely on paired low-fidelity, low-resolution and high-fidelity, high-resolution datasets for training, which are often impossible to acquire in complex flow systems. To address this challenge, we propose a novel two-step approach that eliminates the need for paired datasets. First, we perform unpaired domain translation at the low-resolution level using an Enhanced Denoising Diffusion Implicit Bridge. This process transforms low-fidelity, low-resolution inputs into high-fidelity, low-resolution outputs, and we provide a theoretical analysis to highlight the advantages of this enhanced diffusion-based approach. Second, we employ the cascaded Superresolution via Repeated Refinement model to upscale the high-fidelity, low-resolution prediction to the high-resolution result. We demonstrate the effectiveness of our approach across three fluid dynamics problems. Moreover, by incorporating a neural operator to learn system dynamics, our method can be extended to improve evolutionary simulations of low-fidelity, low-resolution data. Reproducibility of computational results. This paper has been awarded the “SIAM Reproducibility Badge: Code and data available” as a recognition that the authors have followed reproducibility principles valued by SISC and the scientific computing community. Code and data that allow readers to reproduce the results in this paper are available at https://github.com/woodssss/Unpaired_SR_demo_code and in the supplementary materials ( M175142_Supplementary_Materials_1.pdf [342KB], Unpaired_SR_demo_code-main.zip [122MB]). [Formula: see text]
Förderung
- National Science Foundation
- Data Science Initiative at the University of Minnesota
- Office of Naval Research
- University of Minnesota
Zitieren
APA
Xu, W., Lu, Y., Shen, L., Xuan, A., & Barzegari, A. (2026). Diffusion-Based Models for Unpaired Superresolution in Fluid Dynamics. SIAM Journal on Scientific Computing, 48(4), C862-C889. https://doi.org/10.1137/25m1751426
Vancouver
Xu W, Lu Y, Shen L, Xuan A, Barzegari A. Diffusion-Based Models for Unpaired Superresolution in Fluid Dynamics. SIAM Journal on Scientific Computing. 2026;48(4):C862-C889. doi:10.1137/25m1751426
BibTeX
@article{Xu2026,
author = {Xu, Wuzhe and Lu, Yulong and Shen, Lian and Xuan, Anqing and Barzegari, Ali},
title = {Diffusion-Based Models for Unpaired Superresolution in Fluid Dynamics},
journal = {SIAM Journal on Scientific Computing},
year = {2026},
volume = {48},
number = {4},
pages = {C862--C889},
doi = {10.1137/25m1751426}
}
EUVIMED