Supervising the Path to Fine Scales: GalerkinFlow for Scientific-Field and Image Super-Resolution

Excerpt

arXiv:2608.16546v1 Announce Type: cross Abstract: Most super-resolution models learn from paired data by supervising only the final high-resolution output. This provides little control over how the prediction should evolve between the downsampled observation and its fine target. We introduce GalerkinFlow, an equation-agnostic framework that turns each coarse--fine pair into supervision along an entire reconstruction path. At a random sample of intermediate states on the reconstruction path, the