Retrieving nanostructure images from spectra

Michael Mrejen, Itzik Malkiel, Lior Wolf, Haim Suchowski

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


We introduce spectra2pix, a deep neural network trained to generate 2D images of nanostructures based on their transmission spectra. Owing to this architecture, our model can be trained for the design of any arbitrary geometry.

Original languageEnglish
Title of host publicationCLEO
Subtitle of host publicationQELS_Fundamental Science, CLEO_QELS 2020
PublisherOSA - The Optical Society
ISBN (Electronic)9781557528209
StatePublished - 2020
EventCLEO: QELS_Fundamental Science, CLEO_QELS 2020 - Washington, United States
Duration: 10 May 202015 May 2020

Publication series

NameOptics InfoBase Conference Papers
VolumePart F182-CLEO-QELS 2020


ConferenceCLEO: QELS_Fundamental Science, CLEO_QELS 2020
Country/TerritoryUnited States


Dive into the research topics of 'Retrieving nanostructure images from spectra'. Together they form a unique fingerprint.

Cite this