Qin Yi, Wan Shujia, Wan Yuhong, Weng Jiawen, Liu Wei, Gong Qiong
Appl Opt. 2020 Aug 20;59(24):7258-7267. doi: 10.1364/AO.399715.
In this paper a novel, to the best of our knowledge, deep neural network (DNN), VUR-Net, is proposed to realize direct and accurate phase unwrapping. The VUR-Net employs a relatively large number of filters in each layer and adopts alternately two types of residual blocks throughout the network, distinguishing it from the previously reported ones. The proposed method enables the wrapped phase map to be unwrapped precisely without any preprocessing or postprocessing operations, even though the map has been degraded by various adverse factors, such as noise, undersampling, deforming, and so on. We compared the VUR-Net with another two state-of-the-art phase unwrapping DNNs, and the corresponding results manifest that our proposal markedly outperforms its counterparts in both accuracy and robustness. In addition, we also developed two new indices to evaluate the phase unwrapping. These indices are proved to be effective and powerful as good candidates for estimating the quality of phase unwrapping.
据我们所知，本文提出了一种新颖的深度神经网络（DNN）——VUR-Net，以实现直接且准确的相位解缠。VUR-Net在每一层使用了相对大量的滤波器，并在整个网络中交替采用两种类型的残差块，这使其有别于先前报道的网络。所提出的方法能够精确地对包裹相位图进行解缠，而无需任何预处理或后处理操作，即使该图已因各种不利因素（如噪声、欠采样、变形等）而退化。我们将VUR-Net与另外两种最先进的相位解缠DNN进行了比较，相应结果表明，我们的方法在准确性和鲁棒性方面均明显优于其他方法。此外，我们还开发了两个新指标来评估相位解缠。事实证明，这些指标作为估计相位解缠质量的良好候选指标是有效且强大的。
