The global low-resolution and patched high-resolution signed distance functions (SDFs) are fed to networks G₀ and G₁. The patched features (256 × 256) from G₀ are merged with the down-sampled features (256 × 256) by G₁ to predict the patched high-resolution flow field. Since the elementwise sum of the global features from G₀ and the local features from G₁ allows the propagation of the global information to G₁, the predicted high-resolution flow fields maintain the consistency of the structures between the patches.