PI-AstroDeconv：一种用于天文图像反卷积的物理信息无监督学习方法
PI-AstroDeconv: A Physics-Informed Unsupervised Learning Method for Astronomical Image Deconvolution
AI总结：
本文提出 PI-AstroDeconv，一种融合望远镜 PSF 物理先验的无监督编码器-解码器架构，利用 FFT 卷积高效处理高分辨率天文图像，并比较 AE 与 U-Net 等回归网络。
摘要：
在天文望远镜的成像过程中，对其光束或点扩散函数（Point Spread Function，PSF）进行反卷积是一项至关重要的任务。然而，反卷积是一个经典且具有挑战性的逆计算问题。在光束或 PSF 复杂或测量不准确的场景中，例如干涉阵列和某些射电望远镜，由此产生的模糊图像通常难以进行视觉解译，也难以使用传统物理检测方法进行分析。我们认为，传统方法往往缺乏特定的先验知识，从而导致性能欠佳。为解决这一问题并实现图像反卷积与重建，我们提出了一种融入先验物理信息的无监督网络架构。该网络采用编码器-解码器结构，同时利用望远镜的 PSF 作为先验知识。在网络训练过程中，我们引入了加速的快速傅里叶变换（Fast Fourier Transform，FFT）卷积，以实现对高分辨率输入图像和 PSF 的高效处理。我们探索了多种经典回归网络，包括自编码器（autoencoder，AE）和 U-Net，并通过对比分析进行了全面的性能评估。
英文摘要：
In the imaging process of an astronomical telescope, the deconvolution of its beam or Point Spread Function (PSF) is a crucial task. However, deconvolution presents a classical and challenging inverse computation problem. In scenarios where the beam or PSF is complex or inaccurately measured, such as in interferometric arrays and certain radio telescopes, the resultant blurry images are often challenging to interpret visually or analyze using traditional physical detection methods. We argue that traditional methods frequently lack specific prior knowledge, thereby leading to suboptimal performance. To address this issue and achieve image deconvolution and reconstruction, we propose an unsupervised network architecture that incorporates prior physical information. The network adopts an encoder-decoder structure while leveraging the telescope's PSF as prior knowledge. During network training, we introduced accelerated Fast Fourier Transform (FFT) convolution to enable efficient processing of high-resolution input images and PSFs. We explored various classic regression networks, including autoencoder (AE) and U-Net, and conducted a comprehensive performance evaluation through comparative analysis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
