Marcus Carlsson — accepted AI-conference papers

2025

Estimating Instrument Spectral Response Functions Using Sparse Representations and Quadratic Envelopes

Jihanne El Haouari, Marcus Carlsson, Jean-Yves Tourneret, Herwig Wendt, Jean-Michel Gaucel, Christelle Pittet

ICASSP 2025accepted

The estimation of high resolution spectrometer Instrument Spectral Response Functions (ISRFs) is crucial because an imperfect knowledge of these functions can induce errors in the measurements. The state-of-the-art for this problem currently relies on the use of parametric models, which frequently l…

Cited by 0 Source ↗Scholar ↗

2024

Plug-And-Play Algorithm Coupled with Low-Rank Quadratic Envelope Regularization for Compressive Spectral Imaging

Jorge Bacca, Marcus Carlsson, Brayan Monroy, Henry Arguello

ICASSP 2024accepted

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, synergi…

Cited by 0 Source ↗Scholar ↗

2019

Quadratic Envelope Regularization for Structured Low Rank Approximation

Jamie Caprani, Marcus Carlsson

ICASSP 2019accepted

Compressed sensing techniques, such as nuclear norm minimization, can be used for structured low rank approximation, but it is well known that these methods lead to suboptimal results. In this article we consider how to improve this approach by use of so called "quadratic envelopes". The new feature…

Cited by 0 Source ↗Scholar ↗

2017

Non-Convex Rank/Sparsity Regularization and Local Minima

Carl Olsson, Marcus Carlsson, Fredrik Andersson, Viktor Larsson

ICCV 2017poster

This paper considers the problem of recovering either a low rank matrix or a sparse vector from observations of linear combinations of the vector or matrix elements. Recent methods replace the non-convex regularization with l1 or nuclear norm relaxations. It is well known that this approach recovers…

Cited by 24 PDF ↗Scholar ↗