cs.CVNov 18, 2026

STAR++: A Physical-Aware Benchmark and Framework for Astronomical Super-Resolution across Multiple Filters

Authors: Guohang Zhuang, Jiaze Li, Kuo-cheng Wu, Hao Du, Jinyang Huang, Xiang Zhang, Wanli Ouyang, Yan Lu

Organizations: School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230026, China · Shanghai Artificial Intelligence Laboratory, Shanghai 200240, China · University of Science and Technology of China, Hefei · The Chinese University of Hong Kong, Hong Kong · 

Abstract

Astronomical super-resolution (ASR) aims to reconstruct high-resolution star fields from low-resolution telescope observations across multiple filters for astrophysical analysis. However, developing a physics-aware ASR framework faces two challenges: 1) Data view: no large-scale benchmark supports field-level ASR, especially on unseen filters. 2) Method view: Existing ASR methods often fail to preserve stellar flux across spatial resolutions. Moreover, ASR requires reconstructing high-frequency components, including accurate star locations and profiles, making it more ill-posed than natural-image SR. To tackle these problems, we introduce STAR++, a large-scale benchmark comprising approximately 1.7 million flux-consistent image pairs across 36 filters, derived from Hubble Space Telescope (HST) observations. STAR++ uses a flux-preserving data generation pipeline to ensure photometric consistency across resolutions and provides the Flux Error (FE) metric to evaluate ASR models from a physical perspective. To address method-level challenges, we propose a Flux-Invariant Super-Resolution Plus (FISR++) model that generalizes to unseen filters while accurately reconstructing flux-consistent high-resolution images. Beyond the flux-preserving modules, FISR++ introduces two novel components. Specifically, a Filter-Aware Adapter (FAA) incorporates filter metadata to adapt image representations to varying spectral and optical conditions. In addition, a Spatial Ambiguity Disentangle Loss (SADL) models spatial ambiguity as pixel-shift uncertainty, mitigating the smoothing of learned conditional mean reconstructions caused by this ambiguity. Extensive experiments demonstrate that FISR++ consistently outperforms existing ASR methods in reconstruction quality and flux accuracy, while generalizing to unseen filters, highlighting its effectiveness for photometrically faithful ASR.

Figures & tables

Explore similar work

CardsList
  1. FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution

    May 5, 2026Shuhong Liu, Xining Ge, Quanfeng Xu +9Flow MatchingImage Super-Resolution

  2. ASTRA-SR: Atmospheric Seeing and Turbulence Restoration for Astronomical Image Super-Resolution

    Sep 22, 2026Xining Ge, Ziteng Cui, Shuhong LiuImage RestorationImage Super-Resolution

  3. SpatialSR: Spatial Resolution-Centric Pipeline for Arbitrary-Scale Remote Sensing Super-Resolution

    Nov 9, 2026Yan Zhang, Runfeng Luo, Liangke Gao +3Remote Sensing Image Super-ResolutionImage Super-Resolution