Drifting Models for Surrogate Flow Modeling
For engineers and researchers needing rapid indoor environment optimization, this work provides a highly efficient alternative to diffusion-based surrogates, addressing the speed bottleneck of generative models in CFD.
The paper adapts the drifting generative framework to fluid mechanics, achieving a surrogate model that matches iterative diffusion in accuracy and flow consistency while running two orders of magnitude faster, enabling real-time CFD surrogates.
While Computational Fluid Dynamics (CFD) provides high-fidelity flow fields for optimizing indoor environments, its computational cost limits rapid exploration. To solve this problem generative surrogates offer better distribution modeling than deterministic networks, but iterative sampling is slow. To enable high-quality, single-pass generation, we adapt the novel generative drifting framework to fluid mechanics. We introduce a conditional architecture that performs drifting in a learned VAE latent space and uses label-aware masking to align generated samples with their boundary conditions. Our label-conditioned model matches iterative diffusion in accuracy and flow consistency while running two orders of magnitude faster. Additionally, we propose a spatial-conditioning variant that establishes a promising path towards generalization to unseen geometries. Ultimately, conditional drifting serves as a highly efficient alternative to diffusion based approaches, unlocking real-time CFD surrogates where inference speed is critical.