GeoFunFlow-3D reduces pressure-field RRMSE to 0.0215 on industrial 3D datasets by combining flow matching with physics-guided components that target spectral bias and localized shock structures.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GeoFunFlow-3D: A Physics-Guided Generative Flow Matching Framework for High-Fidelity 3D Aerodynamic Inference over Complex Geometries
GeoFunFlow-3D reduces pressure-field RRMSE to 0.0215 on industrial 3D datasets by combining flow matching with physics-guided components that target spectral bias and localized shock structures.