FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution

2026-05-05

AI Summary

Ground-based astronomical images are inherently limited by atmospheric seeing and pixel sampling, making it challenging to reconstruct high-resolution spatial images with physically meaningful fidelity; existing methods often produce oversmoothed results or spurious astrophysical sources. This work proposes a conservative pixel-level flow-matching framework that integrates observation uncertainty modeling and source-region importance weighting during training, and introduces an untrained Wiener regularization correction at test time to effectively suppress artifacts while preserving genuine structural details. To our knowledge, this is the first approach to combine conservative flow matching with Wiener regularization for astronomical super-resolution. The authors also construct DESI–HST, a large-scale paired dataset incorporating realistic variations in atmospheric point spread functions. Experiments demonstrate that the proposed method significantly outperforms current state-of-the-art techniques in photometric accuracy and scientific reliability, achieving high detail fidelity with minimal spurious features.

Abstract

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.

Problem

• astronomical super-resolution
• atmospheric seeing
• PSF variation
• hallucination
• ground-to-space imaging

Innovation

• conservative flow-matching
• astronomical super-resolution
• observation uncertainty
• hallucination suppression
• real-world PSF variation