4 citations · 9 across the 7 of their papers we have counts for
10 papers
Guidance Without Labels: Flow Matching from Coupled Gaussian Mixtures
Stanislas Ducotterd, Bassam El Rawas, Michael Unser
Flow matching models are typically trained to transport a Gaussian source to the data distribution, with source and target samples paired independently. We replace the source with…
Learning Regularization Functionals for Inverse Problems: A Comparative Study
Johannes Hertrich, Hok Shing Wong, Alexander Denker +16
In recent years, a variety of learned regularization frameworks for solving inverse problems in imaging have emerged. These offer flexible modeling together with mathematical insig…
Breaking the Weak Recovery Limit in Random Phase Retrieval with Learned Regularizers
Stanislas Ducotterd, Zhiyuan Hu, Michael Unser +1
We seek to recover an unknown signal from nonlinear amplitude-only measurements, a challenging inverse problem. Strong theoretical guarantees have been established for idealized ra…
Multivariate Fields of Experts for Convergent Image Reconstruction
Stanislas Ducotterd, Michael Unser
We introduce the multivariate fields of experts, a new framework for the learning of image priors. Our model generalizes existing fields of experts methods by incorporating multiva…
Universal Architectures for the Learning of Polyhedral Norms and Convex Regularizers
Michael Unser, Stanislas Ducotterd
This paper addresses the task of learning convex regularizers to guide the reconstruction of images from limited data. By imposing that the reconstruction be amplitude-equivariant,…
Learning of Patch-Based Smooth-Plus-Sparse Models for Image Reconstruction
Stanislas Ducotterd, Sebastian Neumayer, Michael Unser
We aim at the solution of inverse problems in imaging, by combining a penalized sparse representation of image patches with an unconstrained smooth one. This allows for a straightf…
Parseval Convolution Operators and Neural Networks
Michael Unser, Stanislas Ducotterd
We first establish a kernel theorem that characterizes all linear shift-invariant (LSI) operators acting on discrete multicomponent signals. This result naturally leads to the iden…
Controlled Learning of Pointwise Nonlinearities in Neural-Network-Like Architectures
Michael Unser, Alexis Goujon, Stanislas Ducotterd
We present a general variational framework for the training of freeform nonlinearities in layered computational architectures subject to some slope constraints. The regularization…
A Neural-Network-Based Convex Regularizer for Inverse Problems
Alexis Goujon, Sebastian Neumayer, Pakshal Bohra +2
The emergence of deep-learning-based methods to solve image-reconstruction problems has enabled a significant increase in reconstruction quality. Unfortunately, these new methods o…
Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions
Stanislas Ducotterd, Alexis Goujon, Pakshal Bohra +3
Lipschitz-constrained neural networks have several advantages over unconstrained ones and can be applied to a variety of problems, making them a topic of attention in the deep lear…