扩散模型用于相关散斑噪声下环星环境的偏振重建
Diffusion Models for Polarimetric Reconstruction of Circumstellar Environments in Correlated Speckle Noise
查看机构详情
- Université Côte d'Azur（蔚蓝海岸大学）
- EPITA（EPITA高等计算机学院）
- Univ. Lyon 1, ENS de Lyon（里昂第一大学，巴黎高等师范学校里昂分校）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本文扩展RHAPSODIE框架，利用扩散模型先验处理相关散斑噪声下的偏振重建，显著优于Tikhonov正则化并媲美即插即用基线，成功恢复被噪声掩盖的环星盘形态特征。
中文摘要 AI 辅助
高对比度偏振成像对环星盘的观测受到恒星泄漏和散斑噪声的严重限制。基于RHAPSODIE框架处理偏振逆问题，扩散方法通过用学习先验替代经典正则化已显示出有前景的结果。然而，RHAPSODIE的白噪声假设未能捕捉大气和仪器散斑的空间相关结构。我们扩展该框架以处理散斑波动，将其建模为具有平稳协方差矩阵和具有高斯谱密度的平稳协方差矩阵的高斯场。为了高效应用包含相关散斑和异方差光子噪声的稠密精度矩阵，我们开发了一种专门用于共轭梯度迭代的预处理器。扩散先验仅使用盘面数据训练。尽管在极低信噪比下仍存在局限，我们的方法显著优于Tikhonov正则化，并在现实场景中与Plug-and-Play基线表现相当，成功恢复了被相关噪声掩盖的形态特征。
英文摘要
High-contrast polarimetric imaging of circumstellar disks is severely limited by stellar leakage and speckle noise. Building upon the RHAPSODIE framework for polarimetric inverse problems, diffusion-based methods have shown promising results by replacing classical regularization with learned priors. However, RHAPSODIE's white noise assumption fails to capture the spatial correlation structure of atmospheric and instrumental speckles. We extend this framework to handle speckle fluctuations, which are modeled as a Gaussian field with a stationary covariance matrix with a Gaussian spectral density. To efficiently apply the dense precision matrix that includes correlated speckle and heteroskedastic photon noise, we develop a dedicated preconditioner for conjugate gradient iterations. The diffusion prior is trained exclusively on disk-only data. While limitations remain at very low SNRs, our method significantly outperforms Tikhonov regularization and competes favorably with a Plug-and-Play baseline in realistic regimes, successfully recovering morphological features masked by correlated noise.
