Saved in:
Bibliographic Details
Main Authors: Trupin, Noah, Ghosh, Rahul, Jangid, Aadi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.17773
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912915075891200
author Trupin, Noah
Ghosh, Rahul
Jangid, Aadi
author_facet Trupin, Noah
Ghosh, Rahul
Jangid, Aadi
contents We present a generative modeling framework for synthesizing physically feasible two-dimensional incompressible flows under arbitrary obstacle geometries and boundary conditions. Whereas existing diffusion-based flow generators either ignore physical constraints, impose soft penalties that do not guarantee feasibility, or specialize to fixed geometries, our approach integrates three complementary components: (1) a boundary-conditioned diffusion model operating on velocity fields; (2) a physics-informed training objective incorporating a divergence penalty; and (3) a projection-constrained reverse diffusion process that enforces exact incompressibility through a geometry-aware Helmholtz-Hodge operator. We derive the method as a discrete approximation to constrained Langevin sampling on the manifold of divergence-free vector fields, providing a connection between modern diffusion models and geometric constraint enforcement in incompressible flow spaces. Experiments on analytic Navier-Stokes data and obstacle-bounded flow configurations demonstrate significantly improved divergence, spectral accuracy, vorticity statistics, and boundary consistency relative to unconstrained, projection-only, and penalty-only baselines. Our formulation unifies soft and hard physical structure within diffusion models and provides a foundation for generative modeling of incompressible fields in robotics, graphics, and scientific computing.
format Preprint
id arxiv_https___arxiv_org_abs_2602_17773
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Flow Distributions via Projection-Constrained Diffusion on Manifolds
Trupin, Noah
Ghosh, Rahul
Jangid, Aadi
Fluid Dynamics
Machine Learning
We present a generative modeling framework for synthesizing physically feasible two-dimensional incompressible flows under arbitrary obstacle geometries and boundary conditions. Whereas existing diffusion-based flow generators either ignore physical constraints, impose soft penalties that do not guarantee feasibility, or specialize to fixed geometries, our approach integrates three complementary components: (1) a boundary-conditioned diffusion model operating on velocity fields; (2) a physics-informed training objective incorporating a divergence penalty; and (3) a projection-constrained reverse diffusion process that enforces exact incompressibility through a geometry-aware Helmholtz-Hodge operator. We derive the method as a discrete approximation to constrained Langevin sampling on the manifold of divergence-free vector fields, providing a connection between modern diffusion models and geometric constraint enforcement in incompressible flow spaces. Experiments on analytic Navier-Stokes data and obstacle-bounded flow configurations demonstrate significantly improved divergence, spectral accuracy, vorticity statistics, and boundary consistency relative to unconstrained, projection-only, and penalty-only baselines. Our formulation unifies soft and hard physical structure within diffusion models and provides a foundation for generative modeling of incompressible fields in robotics, graphics, and scientific computing.
title Learning Flow Distributions via Projection-Constrained Diffusion on Manifolds
topic Fluid Dynamics
Machine Learning
url https://arxiv.org/abs/2602.17773