Sampling for Snapshot Compressive Imaging

In this study, we compare interlaced and multiscale sampling of smooth manifolds for snapshot compressive imaging. With a particular focus on spectral, spatial, and temporal focal photographic imaging systems, we show that structured transformer networks enable the efficient integration of multiscal...

Full description

Saved in:
Bibliographic Details
Published in:Intelligent computing 2023-01, Vol.2
Main Authors: Hu, Minghao, Wu, Zongliang, Huang, Qian, Yuan, Xin, Brady, David
Format: Article
Language:English
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this study, we compare interlaced and multiscale sampling of smooth manifolds for snapshot compressive imaging. With a particular focus on spectral, spatial, and temporal focal photographic imaging systems, we show that structured transformer networks enable the efficient integration of multiscale manifolds. In the applications considered here, transformer networks enable simpler and more target-specific sampling strategies for compressive tomography.
ISSN:2771-5892
2771-5892
DOI:10.34133/icomputing.0038