29 citations · 52 across the 9 of their papers we have counts for
16 papers
Regularization via deep generative models: an analysis point of view
Thomas Oberlin, Mathieu Verm
This paper proposes a new way of regularizing an inverse problem in imaging (e.g., deblurring or inpainting) by means of a deep generative neural network. Compared to end-to-end mo…
Phase retrieval with Bregman divergences: Application to audio signal recovery
Pierre-Hugo Vial, Paul Magron, Thomas Oberlin +1
Phase retrieval aims to recover a signal from magnitude or power spectra measurements. It is often addressed by considering a minimization problem involving a quadratic cost functi…
Compartment model-based nonlinear unmixing for kinetic analysis of dynamic PET images
Yanna Cruz Cavalcanti, Thomas Oberlin, Vinicius Ferraris +3
When no arterial input function is available, quantification of dynamic PET images requires a previous step devoted to the extraction of a reference time-activity curve (TAC). Fact…
Phase recovery with Bregman divergences for audio source separation
Paul Magron, Pierre-Hugo Vial, Thomas Oberlin +1
Time-frequency audio source separation is usually achieved by estimating the short-time Fourier transform (STFT) magnitude of each source, and then applying a phase recovery algori…
Phase retrieval with Bregman divergences and application to audio signal recovery
Pierre-Hugo Vial, Paul Magron, Thomas Oberlin +1
Phase retrieval (PR) aims to recover a signal from the magnitudes of a set of inner products. This problem arises in many audio signal processing applications which operate on a sh…
Ordinal Non-negative Matrix Factorization for Recommendation
Olivier Gouvert, Thomas Oberlin, Cédric Févotte
We introduce a new non-negative matrix factorization (NMF) method for ordinal data, called OrdNMF. Ordinal data are categorical data which exhibit a natural ordering between the ca…