Convolutional neural network (CNN) has great potentials in holographic reconstruction. Although excellent results can be achieved by using this technique, the number of training and label data must be the same and strict paired relationship is required. Here, we present a new end-to-end learning-based framework to reconstruct noise-free images in absence of any paired training data and prior knowledge of object real distribution. The algorithm uses the cycle consistency loss and generative adversarial network to implement unpaired training method. It is demonstrated by the experiments that high accuracy reconstruction images can be obtained by using unpaired training and label data. Moreover, the unpaired feature of the algorithm makes the system robust to displacement aberration and defocusing effect.

中文翻译：

---

基于非配对数据深度学习框架的数字全息重建

卷积神经网络（CNN）在全息重建方面具有巨大的潜力。虽然使用这种技术可以获得很好的结果，但训练和标签数据的数量必须相同，并且需要严格的配对关系。在这里，我们提出了一种新的基于端到端学习的框架，以在没有任何配对训练数据和对象真实分布的先验知识的情况下重建无噪声图像。该算法使用循环一致性损失和生成对抗网络来实现非配对训练方法。实验证明，利用不成对的训练和标签数据可以获得高精度的重建图像。此外，该算法的非配对特征使系统对位移像差和散焦效应具有鲁棒性。