R.I.P.
๐ป
Ghosted
FlowRefiner: Flow Matching-Based Iterative Refinement for 3D Turbulent Flow Simulation
April 18, 2026 ยท Grace Period ยท + Add venue
Authors
Yilong Dai, Yiming Sun, Yiheng Chen, Shengyu Chen, Xiaowei Jia, Runlong Yu
arXiv ID
2604.17149
Category
physics.flu-dyn
Cross-listed
cs.LG
Citations
0
Abstract
Accurate autoregressive prediction of 3D turbulent flows remains challenging for neural PDE solvers, as small errors in fine-scale structures can accumulate rapidly over rollout. In this paper, we propose FlowRefiner, a flow matching-based iterative refinement framework for 3D turbulent flow simulation. The method replaces stochastic denoising refinement with deterministic ODE-based correction, uses a unified velocity-field regression objective across all refinement stages, and introduces a decoupled sigma schedule that fixes the noise range independently of refinement depth. These design choices yield stable and effective refinement in the small-noise regime. Experiments on large-scale 3D turbulence with rich multi-scale structures show that FlowRefiner achieves state-of-the-art autoregressive prediction accuracy and strong physical consistency. Although developed for turbulent flow simulation, the proposed framework is broadly applicable to iterative refinement problems in scientific modeling.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ physics.flu-dyn
R.I.P.
๐ป
Ghosted
Efficient collective swimming by harnessing vortices through deep reinforcement learning
R.I.P.
๐ป
Ghosted
NVIDIA SimNet^{TM}: an AI-accelerated multi-physics simulation framework
R.I.P.
๐ป
Ghosted
Teaching the Incompressible Navier-Stokes Equations to Fast Neural Surrogate Models in 3D
R.I.P.
๐ป
Ghosted
Prediction of Reynolds Stresses in High-Mach-Number Turbulent Boundary Layers using Physics-Informed Machine Learning
R.I.P.
๐ป
Ghosted