A Joint Convolutional and Spatial Quad-Directional LSTM Network for Phase Unwrapping
This addresses phase unwrapping for applications with limited data, offering fast and accurate results, but it is incremental as it builds on existing CNN and LSTM methods.
The paper tackles the ill-posed problem of phase unwrapping by proposing a CNN with a Spatial Quad-Directional LSTM to recover true phase from wrapped phase, achieving a Normalized Root Mean Square Error of 1.3% at SNR = 0 dB and computational time of 0.054 seconds.
Phase unwrapping is a classical ill-posed problem which aims to recover the true phase from wrapped phase. In this paper, we introduce a novel Convolutional Neural Network (CNN) that incorporates a Spatial Quad-Directional Long Short Term Memory (SQD-LSTM) for phase unwrapping, by formulating it as a regression problem. Incorporating SQD-LSTM can circumvent the typical CNNs' inherent difficulty of learning global spatial dependencies which are vital when recovering the true phase. Furthermore, we employ a problem specific composite loss function to train this network. The proposed network is found to be performing better than the existing methods under severe noise conditions (Normalized Root Mean Square Error of 1.3 % at SNR = 0 dB) while spending a significantly less computational time (0.054 s). The network also does not require a large scale dataset during training, thus making it ideal for applications with limited data that require fast and accurate phase unwrapping.