no code implementations • 12 Apr 2013 • Simon Beckouche, Jean-Luc Starck, Jalal Fadili
Astronomical images suffer a constant presence of multiple defects that are consequences of the intrinsic properties of the acquisition equipments, and atmospheric conditions.
1 code implementation • 26 Aug 2013 • Jérémy Rapin, Jérôme Bobin, Anthony Larue, Jean-Luc Starck
In this context, it is fundamental that the sources to be estimated present some diversity in order to be efficiently retrieved.
1 code implementation • 29 Jul 2014 • Jérémy Rapin, Jérôme Bobin, Anthony Larue, Jean-Luc Starck
In this article, we show how a sparse NMF algorithm coined non-negative generalized morphological component analysis (nGMCA) can be extended to impose non-negativity in the direct domain along with sparsity in a transformed domain, with both analysis and synthesis formulations.
no code implementations • 16 Oct 2014 • Fred Maurice Ngolè Mboula, Jean-Luc Starck, Samuel Ronayette, Koryo Okumura, Jérôme Amiaux
In large-scale spatial surveys, such as the forthcoming ESA Euclid mission, images may be undersampled due to the optical sensors sizes.
1 code implementation • 9 Dec 2014 • Jerome Bobin, Jeremy Rapin, Anthony Larue, Jean-Luc Starck
Blind source separation (BSS) is a very popular technique to analyze multichannel data.
2 code implementations • 7 Mar 2017 • Samuel Farrens, Jean-Luc Starck, Fred Maurice Ngolè Mboula
This work introduces the use of the low-rank matrix approximation as a regularisation prior for galaxy image deconvolution and compares its performance with a standard sparse regularisation technique.
Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics
2 code implementations • 7 Aug 2017 • Morgan A. Schmitz, Matthieu Heitz, Nicolas Bonneel, Fred Maurice Ngolè Mboula, David Coeurjolly, Marco Cuturi, Gabriel Peyré, Jean-Luc Starck
Wasserstein barycenters) between dictionary atoms; such atoms are themselves synthetic histograms in the probability simplex.
no code implementations • 25 Oct 2018 • Julian Merten, Carlo Giocoli, Marco Baldi, Massimo Meneghetti, Austin Peel, Florian Lalande, Jean-Luc Starck, Valeria Pettorino
Based on the DUSTGRAIN-pathfinder suite of simulations, we investigate observational degeneracies between nine models of modified gravity and massive neutrinos.
no code implementations • 25 Oct 2018 • Austin Peel, Florian Lalande, Jean-Luc Starck, Valeria Pettorino, Julian Merten, Carlo Giocoli, Massimo Meneghetti, Marco Baldi
We present a convolutional neural network to identify distinct cosmological scenarios based on the weak-lensing maps they produce.
Cosmology and Nongalactic Astrophysics
no code implementations • 11 Dec 2018 • Khanh-Hung Tran, Fred-Maurice Ngole-Mboula, Jean-Luc Starck
In this paper, we propose a semi-supervised dictionary learning method that uses both the information in labelled and unlabelled data and jointly trains a linear classifier embedded on the sparse codes.
2 code implementations • 1 Aug 2019 • Niall Jeffrey, François Lanusse, Ofer Lahav, Jean-Luc Starck
With a validation set of 8000 simulated DES SV data realisations, compared to Wiener filtering with a fixed power spectrum, the DeepMass method improved the mean-square-error (MSE) by 11 per cent.
Cosmology and Nongalactic Astrophysics
no code implementations • 1 Nov 2019 • Florent Sureau, Alexis Lechat, Jean-Luc Starck
Deconvolution of large survey images with millions of galaxies requires to develop a new generation of methods which can take into account a space variant Point Spread Function (PSF) and have to be at the same time accurate and fast.
1 code implementation • MDPI Applied Sciences 2020 • Zaccharie Ramzi, Philippe Ciuciu, Jean-Luc Starck
Deep learning is starting to offer promising results for reconstruction in Magnetic Resonance Imaging (MRI).
2 code implementations • 13 Sep 2020 • Khanh-Hung Tran, Fred-Maurice Ngole-Mboula, Jean-Luc Starck, Vincent Prost
Supervised Dictionary Learning has gained much interest in the recent decade and has shown significant performance improvements in image classification.
1 code implementation • 13 Sep 2020 • Khanh-Hung Tran, Fred-Maurice Ngole-Mboula, Jean-Luc Starck
Machine Learning in general and Deep Learning in particular has gained much interest in the recent decade and has shown significant performance improvements for many Computer Vision or Natural Language Processing tasks.
3 code implementations • 15 Oct 2020 • Zaccharie Ramzi, Philippe Ciuciu, Jean-Luc Starck
We present a new neural network, the XPDNet, for MRI reconstruction from periodically under-sampled multi-coil data.
Ranked #2 on MRI Reconstruction on fastMRI Brain 8x
1 code implementation • 16 Nov 2020 • Zaccharie Ramzi, Benjamin Remy, Francois Lanusse, Jean-Luc Starck, Philippe Ciuciu
Deep neural networks have proven extremely efficient at solving a wide rangeof inverse problems, but most often the uncertainty on the solution they provideis hard to quantify.
3 code implementations • 9 Dec 2020 • Matthew J. Muckley, Bruno Riemenschneider, Alireza Radmanesh, Sunwoo Kim, Geunu Jeong, Jingyu Ko, Yohan Jun, Hyungseob Shin, Dosik Hwang, Mahmoud Mostapha, Simon Arberet, Dominik Nickel, Zaccharie Ramzi, Philippe Ciuciu, Jean-Luc Starck, Jonas Teuwen, Dimitrios Karkalousos, Chaoping Zhang, Anuroop Sriram, Zhengnan Huang, Nafissa Yakubova, Yvonne Lui, Florian Knoll
Accelerating MRI scans is one of the principal outstanding problems in the MRI research community.
1 code implementation • 5 Jan 2021 • Zaccharie Ramzi, Jean-Luc Starck, Philippe Ciuciu
Deep neural networks have recently been thoroughly investigated as a powerful tool for MRI reconstruction.
no code implementations • 5 Jan 2021 • Virginia Ajani, Jean-Luc Starck, Valeria Pettorino
We present a new summary statistic for weak lensing observables, higher than second order, suitable for extracting non-Gaussian cosmological information and inferring cosmological parameters.
Cosmology and Nongalactic Astrophysics
no code implementations • 23 Feb 2021 • Benjamin Naoto Chiche, Arnaud Woiselle, Joana Frontera-Pons, Jean-Luc Starck
Yet, they fail to incorporate some knowledge about the image formation model, which limits their flexibility.
2 code implementations • ICLR 2022 • Zaccharie Ramzi, Florian Mannel, Shaojie Bai, Jean-Luc Starck, Philippe Ciuciu, Thomas Moreau
In Deep Equilibrium Models (DEQs), the training is performed as a bi-level problem, and its computational complexity is partially driven by the iterative inversion of a huge Jacobian matrix.
2 code implementations • 1 Jun 2021 • Zaccharie Ramzi, Alexandre Vignaud, Jean-Luc Starck, Philippe Ciuciu
We perform a qualitative analysis of performance of XPDNet, a state-of-the-art deep learning approach for MRI reconstruction, compared to GRAPPA, a classical approach.
2 code implementations • 24 Nov 2021 • Tobias Liaudat, Jean-Luc Starck, Martin Kilbinger, Pierre-Antoine Frugier
By adding a differentiable optical forward model into the modeling framework, we change the data-driven modeling space from the pixels to the wavefront.
1 code implementation • CVPR 2022 • Benjamin Naoto Chiche, Arnaud Woiselle, Joana Frontera-Pons, Jean-Luc Starck
Finally, we introduce a new framework of recurrent VSR networks that is both stable and competitive, based on Lipschitz stability theory.
no code implementations • 14 Jan 2022 • Benjamin Remy, Francois Lanusse, Niall Jeffrey, Jia Liu, Jean-Luc Starck, Ken Osato, Tim Schrabback
We introduce a novel methodology allowing for efficient sampling of the high-dimensional Bayesian posterior of the weak lensing mass-mapping problem, and relying on simulations for defining a fully non-Gaussian prior.
2 code implementations • 9 Mar 2022 • Tobias Liaudat, Jean-Luc Starck, Martin Kilbinger, Pierre-Antoine Frugier
We change the data-driven modeling space from the pixels to the wavefront by adding a differentiable optical forward model into the modeling framework.
1 code implementation • 12 Jul 2022 • Denise Lanzieri, François Lanusse, Jean-Luc Starck
We present a new scheme to compensate for the small-scales approximations resulting from Particle-Mesh (PM) schemes for cosmological N-body simulations.
no code implementations • 28 Oct 2022 • Benjamin Remy, Francois Lanusse, Jean-Luc Starck
As the volume and quality of modern galaxy surveys increase, so does the difficulty of measuring the cosmological signal imprinted in galaxy shapes.
no code implementations • 12 Jun 2023 • Tobias Liaudat, Jean-Luc Starck, Martin Kilbinger
Second, we provide an overview of the different physical contributors of the PSF, including the optic- and detector-level contributors and the atmosphere.
1 code implementation • 24 Jun 2023 • Benjamin Naoto Chiche, Julien N. Girard, Joana Frontera-Pons, Arnaud Woiselle, Jean-Luc Starck
Finally, based on the test data, we evaluate the source profile reconstruction performance of the proposed methods and classical image deconvolution algorithm CLEAN applied frame-by-frame.