Litcius/Paper detail

EESANet: edge-enhanced self-attention network for two-dimensional phase unwrapping

Junkang Zhang, Qingguang Li

2021Optics Express41 citationsDOIOpen Access PDF

Abstract

In this paper, we first propose a quantitative indicator to measure the amount of prior information contained in the wrapped phase map. Then, Edge-Enhanced Self-Attention Network is proposed for two-dimensional phase unwrapping. EESANet adopts a symmetrical en-decoder architecture and uses self-designed Serried Residual Blocks as its basic block. We add Atrous Spatial Pyramid Pooling and Positional Self-Attention to the network to obtain the long-distance dependency in phase unwrapping, and we further propose Edge-Enhanced Block to enhance the effective edge features of the wrapped phase map. In addition, weighted cross-entropy loss function is employed to overcome the category imbalance problem. Experiments show that our method has higher precision, stronger robustness and better generalization than the state-of-the-art.

Topics & Concepts

Robustness (evolution)Computer scienceResidualPoolingPyramid (geometry)Phase (matter)Artificial intelligenceMeasure (data warehouse)Block (permutation group theory)AlgorithmOpticsGeneralizationPattern recognition (psychology)Computer visionEnhanced Data Rates for GSM EvolutionSpatial frequencyImage processingImage resolutionEdge detectionFunction (biology)Phase unwrappingPoint spread functionMathematicsDependency (UML)Network architectureImage qualityArtificial neural networkPhase retrievalSignal processingInformation lossOptical measurement and interference techniquesRobotics and Sensor-Based Localization3D Shape Modeling and Analysis