Plug-And-Play Algorithm Coupled with Low-Rank Quadratic Envelope Regularization for Compressive Spectral Imaging
(2024) 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings p.2505-2509- Abstract
This paper introduces a plug-and-play algorithm for enhancing compressive spectral imaging (CSI) through the integration of both a quadratic envelope (QE) regularizer and a deep prior. Our method employs the QE-based regularizer to foster a low-rank structure in conjunction with deep priors, synergistically integrated within a Plug-and-Play (PnP) framework. The distinct advantage of our chosen QE-regularizer is its propensity for uncovering low-rank solutions devoid of bias, distinguishing it from the nuclear norm. Through this fusion of QE and deep priors, we harness the complementary strengths of both techniques, resulting in a mutually reinforcing effect for CSI.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/0a95a752-f455-4d93-bccd-ec886846407d
- author
- Bacca, Jorge ; Carlsson, Marcus LU ; Monroy, Brayan and Arguello, Henry
- organization
- publishing date
- 2024
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Compressive Spectral Imaging, Low-Rank Priors, Plug-and-Play ADMM, Quadratic Envelope Regularization
- host publication
- ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- series title
- ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
- pages
- 5 pages
- conference name
- 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
- conference location
- Seoul, Korea, Republic of
- conference dates
- 2024-04-14 - 2024-04-19
- external identifiers
-
- scopus:105001659351
- ISSN
- 1520-6149
- DOI
- 10.1109/ICASSP48485.2024.10447145
- language
- English
- LU publication?
- yes
- id
- 0a95a752-f455-4d93-bccd-ec886846407d
- date added to LUP
- 2025-09-11 11:08:53
- date last changed
- 2025-10-14 09:41:17
@inproceedings{0a95a752-f455-4d93-bccd-ec886846407d,
abstract = {{<p>This paper introduces a plug-and-play algorithm for enhancing compressive spectral imaging (CSI) through the integration of both a quadratic envelope (QE) regularizer and a deep prior. Our method employs the QE-based regularizer to foster a low-rank structure in conjunction with deep priors, synergistically integrated within a Plug-and-Play (PnP) framework. The distinct advantage of our chosen QE-regularizer is its propensity for uncovering low-rank solutions devoid of bias, distinguishing it from the nuclear norm. Through this fusion of QE and deep priors, we harness the complementary strengths of both techniques, resulting in a mutually reinforcing effect for CSI.</p>}},
author = {{Bacca, Jorge and Carlsson, Marcus and Monroy, Brayan and Arguello, Henry}},
booktitle = {{ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}},
issn = {{1520-6149}},
keywords = {{Compressive Spectral Imaging; Low-Rank Priors; Plug-and-Play ADMM; Quadratic Envelope Regularization}},
language = {{eng}},
pages = {{2505--2509}},
series = {{ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings}},
title = {{Plug-And-Play Algorithm Coupled with Low-Rank Quadratic Envelope Regularization for Compressive Spectral Imaging}},
url = {{http://dx.doi.org/10.1109/ICASSP48485.2024.10447145}},
doi = {{10.1109/ICASSP48485.2024.10447145}},
year = {{2024}},
}