Compressive hyperspectral image reconstruction with deep neural networks

Yaron Heiser, Yaniv Oiknine, Adrian Stern

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

9 Scopus citations


In the recent years, we have developed several architectures for compressive hyperspectral (HS) imagers. The compressive sensing (CS) design has allowed the reduction of the enormous acquisition effort associated with the huge dimensionality of the HS data. Unfortunately, the reduced sensing effort offered by the CS approach comes on the account of increased post-sensing computational burden. Conventional CS reconstruction involves algorithms that solve a ℓ1 minimization problem. Those algorithms are iterative and typically very computationally heavy. The computation burden is even more prominent when reconstructing 3D HS data, where each spectral image may have Gigavoxel size. Motivated by this, we have investigated replacing the CS iterative reconstruction step with an appropriate Deep Neural Network.

Original languageEnglish
Title of host publicationBig Data
Subtitle of host publicationLearning, Analytics, and Applications
EditorsFauzia Ahmad
ISBN (Electronic)9781510626430
StatePublished - 1 Jan 2019
EventBig Data: Learning, Analytics, and Applications 2019 - Baltimore, United States
Duration: 17 Apr 201918 Apr 2019

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


ConferenceBig Data: Learning, Analytics, and Applications 2019
Country/TerritoryUnited States


  • Compressive sensing
  • Compressive spectroscopy
  • Deep Neural Networks
  • Hyperspectral imaging

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Compressive hyperspectral image reconstruction with deep neural networks'. Together they form a unique fingerprint.

Cite this