Show simple item record

dc.contributor.authorBaek, Seung-Hwan
dc.contributor.authorIkoma, Hayato
dc.contributor.authorJeon, Daniel S.
dc.contributor.authorLi, Yuqi
dc.contributor.authorHeidrich, Wolfgang
dc.contributor.authorWetzstein, Gordon
dc.contributor.authorKim, Min H.
dc.date.accessioned2020-09-14T11:33:54Z
dc.date.available2020-09-14T11:33:54Z
dc.date.issued2020-09-01
dc.identifier.urihttp://hdl.handle.net/10754/665123
dc.description.abstractTo extend the capabilities of spectral imaging, hyperspectral and depth imaging have been combined to capture the higher-dimensional visual information. However, the form factor of the combined imaging systems increases, limiting the applicability of this new technology. In this work, we propose a monocular imaging system for simultaneously capturing hyperspectral-depth (HS-D) scene information with an optimized diffractive optical element (DOE). In the training phase, this DOE is optimized jointly with a convolutional neural network to estimate HS-D data from a snapshot input. To study natural image statistics of this high-dimensional visual data and to enable such a machine learning-based DOE training procedure, we record two HS-D datasets. One is used for end-to-end optimization in deep optical HS-D imaging, and the other is used for enhancing reconstruction performance with a real-DOE prototype. The optimized DOE is fabricated with a grayscale lithography process and inserted into a portable HS-D camera prototype, which is shown to robustly capture HS-D information. In extensive evaluations, we demonstrate that our deep optical imaging system achieves state-of-the-art results for HS-D imaging and that the optimized DOE outperforms alternative optical designs.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/2009.00463
dc.rightsArchived with thanks to arXiv
dc.titleEnd-to-End Hyperspectral-Depth Imaging with Learned Diffractive Optics
dc.typePreprint
dc.contributor.departmentComputational Imaging Group
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentVisual Computing Center (VCC)
dc.eprint.versionPre-print
dc.contributor.institutionKAIST
dc.contributor.institutionStanford University
dc.identifier.arxivid2009.00463
kaust.personLi, Yuqi
kaust.personHeidrich, Wolfgang
refterms.dateFOA2020-09-14T11:36:01Z


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
14.27Mb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record