6 papers
Training Flow Matching: The Role of Weighting and Parameterization
Anne Gagneux, Ségolène Martin, Rémi Gribonval +1
We study the training objectives of denoising-based generative models, with a particular focus on loss weighting and output parameterization, including noise-, clean image-, and ve…
The Generation Phases of Flow Matching: a Denoising Perspective
Anne Gagneux, Ségolène Martin, Rémi Gribonval +1
Flow matching has achieved remarkable success, yet the factors influencing the quality of its generation process remain poorly understood. In this work, we adopt a denoising perspe…
Proximal Operators of Sorted Nonconvex Penalties
Anne Gagneux, Mathurin Massias, Emmanuel Soubies
This work studies the problem of sparse signal recovery with automatic grouping of variables. To this end, we investigate sorted nonsmooth penalties as a regularization approach fo…
On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
Quentin Bertrand, Anne Gagneux, Mathurin Massias +1
Modern deep generative models can now produce high-quality synthetic samples that are often indistinguishable from real training data. A growing body of research aims to understand…
Convexity in ReLU Neural Networks: beyond ICNNs?
Anne Gagneux, Mathurin Massias, Emmanuel Soubies +1
Convex functions and their gradients play a critical role in mathematical imaging, from proximal optimization to Optimal Transport. The successes of deep learning has led many to u…
PnP-Flow: Plug-and-Play Image Restoration with Flow Matching
Ségolène Martin, Anne Gagneux, Paul Hagemann +1
In this paper, we introduce Plug-and-Play (PnP) Flow Matching, an algorithm for solving imaging inverse problems. PnP methods leverage the strength of pre-trained denoisers, often…