FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution
For astronomers needing high-resolution space-quality images from ground-based telescopes, this method reduces hallucination and improves physical fidelity, addressing a key bottleneck in observational astronomy.
FluxFlow introduces a conservative flow-matching framework for astronomical image super-resolution that handles stochastic, spatially varying PSFs, achieving superior photometric and scientific accuracy over existing methods on a new real-world benchmark of 19,500 ground-to-space image pairs.
Ground-to-space astronomical super-resolution requires recovering space-quality images from ground-based observations that are simultaneously limited by pixel sampling resolution and atmospheric seeing, which imposes a stochastic, spatially varying PSF that cannot be resolved through upsampling alone. Existing methods rely on synthetic training pairs that fail to capture real atmospheric statistics and are prone to either over-smoothed reconstructions or hallucination sources with no physical counterpart in the observed sky. We propose FluxFlow, a conservative pixel-space flow-matching framework that incorporates observation uncertainty and source-region importance weights during training, and a training-free Wiener-regularized test-time correction to suppress hallucination sources while preserving recovered detail. We further construct the DESI--HST Dataset, the large-scale real-world benchmark comprising 19,500 real co-registered ground-to-space image pairs with real atmospheric PSF variation. Experiments demonstrate that FluxFlow consistently outperforms existing baseline methods in both photometric and scientific accuracy.