Y4-Net: a deep learning solution to one-shot dual-wavelength digital holographic reconstruction
Kaiqiang Wang, Qian Kemao, Jianglei Di, Jianlin Zhao
Abstract
In this Letter, a deep learning solution (Y4-Net, four output channels network) to one-shot dual-wavelength digital holography is proposed to simultaneously reconstruct the complex amplitude information of both wavelengths from a single digital hologram with high efficiency. In the meantime, by using single-wavelength results as network ground truth to train the Y4-Net, the challenging spectral overlapping problem in common-path situations is solved with high accuracy.
Topics & Concepts
HolographyDigital holographyOpticsWavelengthComputer scienceNet (polyhedron)Dual (grammatical number)Shot (pellet)PhysicsOne shotPath (computing)Artificial intelligenceMaterials scienceMathematicsArtMetallurgyEngineeringMechanical engineeringGeometryLiteratureProgramming languageDigital Holography and MicroscopyOptical measurement and interference techniquesAdvanced Optical Imaging Technologies