arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.08288cs.CVcs.LGeess.IVphysics.optics
收藏

基于物理一致性的全息图重建自监督学习

Self-supervised learning of hologram reconstruction using physics consistency

University of California, Los Angeles(加州大学洛杉矶分校);California NanoSystems Institute (CNSI)(加州纳米系统研究所);David Geffen School of Medicine(大卫·格芬医学院)

Luzhe Huang, Hanlong Chen, Tairan Liu, Aydogan Ozcan

AI总结:

本文提出自监督学习模型 GedankenNet,仅用物理一致性损失和合成随机图像训练,无需实验或标签数据,即可泛化重建多种生物样本全息图的相位与振幅,并对物理模型扰动具有鲁棒性。

摘要:

过去十年见证了深度学习在各种计算成像、传感和显微任务中的变革性应用。由于采用监督学习方案,这些方法大多依赖大规模、多样化和带标签的训练数据。此类训练图像数据集的获取和准备往往费时费力且成本高昂,同时还会导致有偏估计和对新样本类型的泛化能力有限。在此,我们报告了一种名为 GedankenNet 的自监督学习模型,该模型无需带标签或实验训练数据,并展示了其在全息图重建任务上的有效性和优越泛化能力。在不知道待成像样本类型先验知识的情况下,该自监督学习模型使用物理一致性损失和人工随机图像进行训练,这些图像完全通过合成生成,不涉及任何实验,也不类似于真实世界样本。经过自监督训练后,GedankenNet 成功泛化到多种未见过的生物样本的实验全息图,利用实验获取的测试全息图重建了不同类型物体的相位和振幅图像。在没有获取实验数据、不了解真实感兴趣样本或其空间特征的情况下,GedankenNet 的自监督学习实现了与麦克斯韦方程组一致的复值图像重建,其输出推断和物体解准确表征了自由空间中的波传播。GedankenNet 框架还表现出对物理前向模型中随机未知扰动的鲁棒性,包括全息图距离、像素尺寸和照明波长的变化。这种面向图像重建任务的自监督学习为全息术、显微学和计算成像领域的各种逆问题创造了新的机会。

英文摘要:

The past decade has witnessed transformative applications of deep learning in various computational imaging, sensing and microscopy tasks. Due to the supervised learning schemes employed, these methods mostly depend on large-scale, diverse, and labeled training data. The acquisition and preparation of such training image datasets are often laborious and costly, also leading to biased estimation and limited generalization to new sample types. Here, we report a self-supervised learning model, termed GedankenNet, that eliminates the need for labeled or experimental training data, and demonstrate its effectiveness and superior generalization on hologram reconstruction tasks. Without prior knowledge about the sample types to be imaged, the self-supervised learning model was trained using a physics-consistency loss and artificial random images that are synthetically generated without any experiments or resemblance to real-world samples. After its self-supervised training, GedankenNet successfully generalized to experimental holograms of various unseen biological samples, reconstructing the phase and amplitude images of different types of objects using experimentally acquired test holograms. Without access to experimental data or knowledge of real samples of interest or their spatial features, GedankenNet's self-supervised learning achieved complex-valued image reconstructions that are consistent with the Maxwell's equations, and its output inference and object solutions accurately represent the wave propagation in free-space. GedankenNet framework also exhibits resilience to random, unknown perturbations in the physical forward model, including changes in the hologram distances, pixel size and illumination wavelength. This self-supervised learning of image reconstruction tasks creates new opportunities for various inverse problems in holography, microscopy and computational imaging fields.

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。

↑