Dynamic Tomography Reconstruction via Low-Rank Modeling with a RED Spatial Prior

Berk Iskender, Marc L. Klasky, Yoram Bresler

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Indynamic imaging, a spatiotemporal object is reconstructed from its inconsistent and undersampled measurements obtained over time. Specifically in dynamic tomography, these measurements correspond to the projections of the time-varying object. In this study, we use the dynamic imaging algorithm RED-PSM, which combines the low-rank partially separable modeling (PSM) with the popular Regularization by Denoising (RED) framework and achieves impressive results in different dynamic scenarios, on the tomographic imaging of materials under dynamic mechanical stresses. We compare RED-PSM with a recent deep prior-based technique and with a PSM method with a simple total variation regularization, and demonstrate the advantages of RED-PSM.

Original languageEnglish (US)
Title of host publication2023 IEEE 9th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages506-510
Number of pages5
ISBN (Electronic)9798350344523
DOIs
StatePublished - 2023
Event9th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2023 - Herradura, Costa Rica
Duration: Dec 10 2023Dec 13 2023

Publication series

Name2023 IEEE 9th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2023

Conference

Conference9th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2023
Country/TerritoryCosta Rica
CityHerradura
Period12/10/2312/13/23

Keywords

  • Dynamic tomography
  • Low rank modeling
  • Regularization by denoising

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Signal Processing
  • Control and Optimization
  • Instrumentation

Fingerprint

Dive into the research topics of 'Dynamic Tomography Reconstruction via Low-Rank Modeling with a RED Spatial Prior'. Together they form a unique fingerprint.

Cite this