Recently, deep learning has yielded transformative success across optics and photonics, especially in optical metrology. Deep neural networks (DNNs) with a fully convolutional architecture (e.g., U-Net and its derivatives) have been widely implemented in an end-to-end manner to accomplish various optical metrology tasks, such as fringe denoising, phase unwrapping, and fringe analysis. However, the task of training a DNN to accurately identify an image-to-image transform from massive input and output data pairs seems at best na?ve, as the physical laws governing the image formation or other domain expertise pertaining to the measurement have not yet been fully exploited in current deep learning practice. To this end, we introduce a physics-informed deep learning method for fringe pattern analysis (PI-FPA) to overcome this limit by integrating a lightweight DNN with a learning-enhanced Fourier transform profilometry (LeFTP) module. By parameterizing conventional phase retrieval methods, the LeFTP module embeds the prior knowledge in the network structure and the loss function to directly provide reliable phase results for new types of samples, while circumventing the requirement of collecting a large amount of high-quality data in supervised learning methods. Guided by the initial phase from LeFTP, the phase recovery ability of the lightweight DNN is enhanced to further improve the phase accuracy at a low computational cost compared with existing end-to-end networks. Experimental results demonstrate that PI-FPA enables more accurate and computationally efficient single-shot phase retrieval, exhibiting its excellent generalization to various unseen objects during training. The proposed PI-FPA presents that challenging issues in optical metrology can be potentially overcome through the synergy of physics-priors-based traditional tools and data-driven learning approaches, opening new avenues to achieve fast and accurate single-shot 3D imaging.

钙钛矿太阳能电池仅用十年左右的时间将效率提升至认证的26.1%，非常接近晶硅太阳能电池26.81%的认证效率，展现出巨大的产业化潜力。当前，钙钛矿太阳能电池器件效率还在提升，然而在器件制备过程中，钙钛矿太阳能电池的性能受到许多不可分割的因素影响，传统方法往往采用试错的方式来优化钙钛矿太阳能电池的制备工艺，花费了大量的时间。贝叶斯优化是一种全局优化算法，在解决人工智能的黑盒问题方面取得了很大的成功。本文利用贝叶斯优化算法对钙钛矿层涉及到的碘化铅（PbI₂）过量百分比、退火温度、退火时间、真空萃取时间四个工艺参数进行优化选择，显著降低了研发成本，缩短了研发时间。通过五轮实验迭代，累计34组工艺条件，制备出了器件效率为23.56%的反型钙钛矿太阳能电池。

为了建立川芎指纹图谱，考察不同剂量⁶⁰Co-γ辐照对川芎8种有效成分的影响，以川芎为材料，采用SHIMADZU Shim-pack GIST C18色谱柱（250 mm×4.6 mm，5 μm）对8种有效成分的标准品和对照品储备液进行分析。设定不同剂量（3 kGy、6 kGy、10 kGy、15 kGy）⁶⁰Co-γ辐照处理川芎，处理后样品通过液相色谱法得到指纹图谱。采用《中药色谱指纹图谱相似度评价系统（2004A版）》对相似度进行评价。结果表明：川芎各成分相似度均大于0.988；在低于10 kGy的射线辐照处理后，川芎的8种有效成分含量无明显差异。结果表明该方法稳定可靠。该研究为辐照技术在川芎品质保障及川芎药材辐照标准的制定提供理论依据和支撑。

针对图像增强算法中普遍存在暗部区域细节丢失、亮部区域过度增强等问题，提出了基于自适应截断模拟曝光和深度融合的增强算法。对原始低照度图像进行模拟曝光，通过卷积网络学习曝光序列对应的权重图并在网络内部实现加权融合，获得增强结果。在生成模拟曝光序列的过程中，对图像进行亮暗区域分割，然后对其进行截断性自适应伽马校正，最后通过引导滤波降噪获得合适的曝光序列。获得多曝光序列后，通过基于空洞卷积的上下文聚合网络，实现快速灵活地加权融合，得到最终增强结果。收集了大量公开数据集，并使用微光夜视相机和三通道真彩色相机收集了实验室环境测试集，在不同数据集上和经典主流算法进行了对比实验。实验结果表明，本算法的NIQE、PSNR和SSIM指标都是最好的，其中NIQE降低了4.49%，PSNR提高了4.28%，SSIM提高了1.94%。此外，算法的色彩还原效果也很好，色差指标是所有算法中最小的，在8.71×10^-2 lx照度下，本算法色差减小了14.83%，在1.02×10^-2 lx下减小了3.05%。本文算法可以明显提高图像亮度和对比度，鲁棒性较好，不会产生过度增强现象，有效恢复图像细节的同时兼顾色彩信息，增强结果真实自然。

We propose a high-accuracy artifacts-free single-frame digital holographic phase demodulation scheme for relatively low-carrier frequency holograms—deep learning assisted variational Hilbert quantitative phase imaging (DL-VHQPI). The method, incorporating a conventional deep neural network into a complete physical model utilizing the idea of residual compensation, reliably and robustly recovers the quantitative phase information of the test objects. It can significantly alleviate spectrum-overlapping-caused phase artifacts under the slightly off-axis digital holographic system. Compared to the conventional end-to-end networks (without a physical model), the proposed method can reduce the dataset size dramatically while maintaining the imaging quality and model generalization. The DL-VHQPI is quantitatively studied by numerical simulation. The live-cell experiment is designed to demonstrate the method's practicality in biological research. The proposed idea of the deep learning-assisted physical model might be extended to diverse computational imaging techniques.