论文标题
使用扩散模型从嘈杂图像中的复杂值检索
Complex-valued Retrievals From Noisy Images Using Diffusion Models
论文作者
论文摘要
在不同的显微镜模式中，传感器仅测量实现的强度。此外，传感器读数还受Poissonian分布的光子噪声的影响。传统的恢复算法通常旨在最大程度地减少原始图像和恢复图像之间的平均误差（MSE）。这通常会导致感觉模糊，感知质量差。最近，事实证明，深度扩散模型（DDMS）能够从受欢迎的变量的A-posteriori概率中取样图像，从而导致视觉上令人愉悦的高质量图像。这些模型主要是针对高斯噪声的真实价值图像提出的。在这项研究中，我们概括了一种DDM退火的Langevin Dynamics（一种DDM），以应对受Poisson噪声影响的复杂值（和真实图像）的光学成像中的基本挑战。我们将算法应用于各种光学方案，例如傅立叶Ptychography，Phase reterieval和Poisson denoisising。我们的算法对模拟和生物经验数据进行了评估。
In diverse microscopy modalities, sensors measure only real-valued intensities. Additionally, the sensor readouts are affected by Poissonian-distributed photon noise. Traditional restoration algorithms typically aim to minimize the mean squared error (MSE) between the original and recovered images. This often leads to blurry outcomes with poor perceptual quality. Recently, deep diffusion models (DDMs) have proven to be highly capable of sampling images from the a-posteriori probability of the sought variables, resulting in visually pleasing high-quality images. These models have mostly been suggested for real-valued images suffering from Gaussian noise. In this study, we generalize annealed Langevin Dynamics, a type of DDM, to tackle the fundamental challenges in optical imaging of complex-valued objects (and real images) affected by Poisson noise. We apply our algorithm to various optical scenarios, such as Fourier Ptychography, Phase Retrieval, and Poisson denoising. Our algorithm is evaluated on simulations and biological empirical data.
