Sat2Flow: A Structure-Aware Diffusion Framework for Human Flow Generation from Satellite Imagery

TL;DR

Sat2Flow is a novel diffusion-based framework that generates human mobility flow matrices from satellite imagery, ensuring structural consistency and robustness without relying on auxiliary data.

Contribution

It introduces a structure-aware diffusion model that maintains topological invariance and uses satellite images alone for OD flow generation, overcoming previous data dependency and fragility issues.

Findings

Outperforms existing methods in accuracy on real datasets.

Maintains flow structure under regional reordering.

Eliminates need for auxiliary features in flow prediction.

Abstract

Origin-Destination (OD) flow matrices are critical for urban mobility analysis, supporting traffic forecasting, infrastructure planning, and policy design. Existing methods face two key limitations: (1) reliance on costly auxiliary features (e.g., Points of Interest, socioeconomic statistics) with limited spatial coverage, and (2) fragility to spatial topology changes, where reordering urban regions disrupts the structural coherence of generated flows. We propose Sat2Flow, a structure-aware diffusion framework that generates structurally coherent OD flows using only satellite imagery. Our approach employs a multi-kernel encoder to capture diverse regional interactions and a permutation-aware diffusion process that maintains consistency across regional orderings. Through joint contrastive training linking satellite features with OD patterns and equivariant diffusion training enforcing structural invariance, Sat2Flow ensures topological robustness under arbitrary regional reindexing. Experiments on real-world datasets show that Sat2Flow outperforms physics-based and data-driven baselines in accuracy while preserving flow distributions and spatial structures under index permutations. Sat2Flow offers a globally scalable solution for OD flow generation in data-scarce environments, eliminating region-specific auxiliary data dependencies while maintaining structural robustness for reliable mobility modeling.