ProFlow: Zero-Shot Physics-Consistent Sampling via Proximal Flow Guidance

TL;DR

ProFlow is a zero-shot sampling method that enforces strict physical and observational constraints in inferring physical fields from sparse data, without retraining the generative model, by using a proximal guidance framework.

Contribution

ProFlow introduces a novel proximal guidance framework for physics-consistent sampling that operates without task-specific retraining of the generative prior.

Findings

Achieves superior physical and observational consistency.

Outperforms diffusion- and flow-based baselines in benchmarks.

Maintains distributional statistics accurately.

Abstract

Inferring physical fields from sparse observations while strictly satisfying partial differential equations (PDEs) is a fundamental challenge in computational physics. Recently, deep generative models offer powerful data-driven priors for such inverse problems, yet existing methods struggle to enforce hard physical constraints without costly retraining or disrupting the learned generative prior. Consequently, there is a critical need for a sampling mechanism that can reconcile strict physical consistency and observational fidelity with the statistical structure of the pre-trained prior. To this end, we present ProFlow, a proximal guidance framework for zero-shot physics-consistent sampling, defined as inferring solutions from sparse observations using a fixed generative prior without task-specific retraining. The algorithm employs a rigorous two-step scheme that alternates between: (\romannumeral1) a terminal optimization step, which projects the flow prediction onto the intersection of the physically and observationally consistent sets via proximal minimization; and (\romannumeral2) an interpolation step, which maps the refined state back to the generative trajectory to maintain consistency with the learned flow probability path. This procedure admits a Bayesian interpretation as a sequence of local maximum a posteriori (MAP) updates. Comprehensive benchmarks on Poisson, Helmholtz, Darcy, and viscous Burgers' equations demonstrate that ProFlow achieves superior physical and observational consistency, as well as more accurate distributional statistics, compared to state-of-the-art diffusion- and flow-based baselines.