[论文解读] Phase Retrieval with Holography and Untrained Priors: Tackling the Challenges of Low-Photon Nanoscale Imaging
该论文提出了一种无需数据集的深度学习框架 HolOpt-P,用于低光子纳米尺度全息相位恢复,结合了物理正向建模与泊松对数似然优化,并引入未经训练的深度图像先验。与经典方法相比,该方法在重建精度和抗噪性、缺失低频分量以及次优参考设计方面表现出更优的鲁棒性,其有效性在模拟和实验光学数据上均得到验证。
Phase retrieval is the inverse problem of recovering a signal from magnitude-only Fourier measurements, and underlies numerous imaging modalities, such as Coherent Diffraction Imaging (CDI). A variant of this setup, known as holography, includes a reference object that is placed adjacent to the specimen of interest before measurements are collected. The resulting inverse problem, known as holographic phase retrieval, is well-known to have improved problem conditioning relative to the original. This innovation, i.e. Holographic CDI, becomes crucial at the nanoscale, where imaging specimens such as viruses, proteins, and crystals require low-photon measurements. This data is highly corrupted by Poisson shot noise, and often lacks low-frequency content as well. In this work, we introduce a dataset-free deep learning framework for holographic phase retrieval adapted to these challenges. The key ingredients of our approach are the explicit and flexible incorporation of the physical forward model into an automatic differentiation procedure, the Poisson log-likelihood objective function, and an optional untrained deep image prior. We perform extensive evaluation under realistic conditions. Compared to competing classical methods, our method recovers signal from higher noise levels and is more resilient to suboptimal reference design, as well as to large missing regions of low frequencies in the observations. Finally, we show that these properties carry over to experimental data acquired on optical wavelengths. To the best of our knowledge, this is the first work to consider a dataset-free machine learning approach for holographic phase retrieval.
研究动机与目标
- 解决全息相干衍射成像(CDI)中低光子、高噪声及不完整傅里叶幅度测量的挑战。
- 开发一种无需数据集的深度学习方法,利用物理先验和未经训练的图像先验,以提升在极端噪声和数据丢失条件下的重建性能。
- 增强对纳米尺度CDI中常见的次优参考设计和缺失低频分量的鲁棒性。
- 在真实模拟数据和实验光学CDI数据上验证该方法,证明其在真实场景中的实用性,而不仅限于合成设置。
提出的方法
- 将全息正向模型集成到自动微分框架中,实现端到端优化,支持可微分物理建模。
- 采用泊松对数似然损失函数以精确建模光子计数噪声,替代标准的最小二乘目标函数。
- 使用未经训练的深度卷积神经网络作为学习到的图像先验,对解进行正则化,而无需依赖外部数据集。
- 框架支持可选的总变差(TV)正则化,以在防止过度平滑的同时保留边缘特征。
- 通过先验图像与重建结果之间特征的分布比较度量(Wasserstein 2-距离)选择超参数(如网络深度)。
- 该方法可扩展至非全息相位恢复及其他成像模式,如叠接衍射成像(ptychography)和光学全息术。
实验结果
研究问题
- RQ1在低光子、高噪声条件下,基于物理信息且无需数据集的深度学习框架是否能优于经典相位恢复方法?
- RQ2当低频分量缺失或受损时,引入未经训练的深度图像先验在多大程度上提升了重建的鲁棒性?
- RQ3在次优参考设计或光阑遮挡导致的数据丢失条件下,该方法的性能保持程度如何?
- RQ4所提出的优化框架是否能泛化到真实世界实验数据(如光学激光CDI)?
- RQ5基于深度特征的分布度量是否可在无真实标签的情况下指导超参数选择?
主要发现
- 在低光子数条件下(例如每像素1个光子),HolOpt-P 的重建保真度显著高于维纳滤波、逆滤波和HIO-Holo,且伪影更少。
- 与经典方法相比,该方法对缺失低频分量和次优参考几何结构更具鲁棒性。
- 在实验光学CDI数据中,HolOpt-P 生成的重建结果在视觉质量上更优,特征更清晰,阴影伪影更少。
- 引入深度解码器可防止仅使用TV正则化时对精细结构(如地平线线)的过度平滑。
- 基于Wasserstein的距离的超参数选择启发式方法成功识别出最优网络深度,且与真实标签数据上的最小均方误差高度相关。
- 该框架在全息CDI之外也展现出良好的泛化潜力,可适用于其他相位恢复模式,如叠接衍射成像和磁性全息术。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。