Astrophotography turbulence mitigation via generative models

TL;DR

AstroDiff is a novel generative diffusion model-based method that significantly improves the quality of ground-based astronomical images degraded by atmospheric turbulence, outperforming existing techniques.

Contribution

The paper introduces AstroDiff, a new generative diffusion model approach for atmospheric turbulence mitigation in astronomical imaging, combining high-quality priors with restoration capabilities.

Findings

AstroDiff achieves higher perceptual quality in turbulence mitigation.

It outperforms existing state-of-the-art methods in structural fidelity.

The method is effective under severe turbulence conditions.

Abstract

Photography is the cornerstone of modern astronomical and space research. However, most astronomical images captured by ground-based telescopes suffer from atmospheric turbulence, resulting in degraded imaging quality. While multi-frame strategies like lucky imaging can mitigate some effects, they involve intensive data acquisition and complex manual processing. In this paper, we propose AstroDiff, a generative restoration method that leverages both the high-quality generative priors and restoration capabilities of diffusion models to mitigate atmospheric turbulence. Extensive experiments demonstrate that AstroDiff outperforms existing state-of-the-art learning-based methods in astronomical image turbulence mitigation, providing higher perceptual quality and better structural fidelity under severe turbulence conditions. Our code and additional results are available at https://web-six-kappa-66.vercel.app/