A Joint Convolutional and Spatial Quad-Directional LSTM Network for Phase Unwrapping

10/26/2020

∙

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 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.

READ FULL TEXT

A Joint Convolutional and Spatial Quad-Directional LSTM Network for Phase Unwrapping

Generative Adversarial Network (GAN) and Enhanced Root Mean Square Error (ERMSE): Deep Learning for Stock Price Movement Prediction

Performance of long short-term memory artificial neural networks in nowcasting during the COVID-19 crisis

Multitask Learning of Temporal Connectionism in Convolutional Networks using a Joint Distribution Loss Function to Simultaneously Identify Tools and Phase in Surgical Videos

LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling

A Novel CNN-LSTM-based Approach to Predict Urban Expansion

A CNN-BiLSTM Model with Attention Mechanism for Earthquake Prediction

Phase Aberration Correction without Reference Data: An Adaptive Mixed Loss Deep Learning Approach

A Joint Convolutional and Spatial Quad-Directional LSTM Network for Phase Unwrapping

Related Research

Generative Adversarial Network (GAN) and Enhanced Root Mean Square Error (ERMSE): Deep Learning for Stock Price Movement Prediction

Performance of long short-term memory artificial neural networks in nowcasting during the COVID-19 crisis

Multitask Learning of Temporal Connectionism in Convolutional Networks using a Joint Distribution Loss Function to Simultaneously Identify Tools and Phase in Surgical Videos

LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling

A Novel CNN-LSTM-based Approach to Predict Urban Expansion

A CNN-BiLSTM Model with Attention Mechanism for Earthquake Prediction

Phase Aberration Correction without Reference Data: An Adaptive Mixed Loss Deep Learning Approach