b'Michael Unser'

research

∙ 08/21/2023

Learning Weakly Convex Regularizers for Convergent Image-Reconstruction Algorithms

We propose to learn non-convex regularizers with a prescribed upper boun...

0 Alexis Goujon, et al. ∙

research

∙ 03/31/2023

On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks

In supervised learning, the regularization path is sometimes used as a c...

0 Sebastian Neumayer, et al. ∙

research

∙ 11/22/2022

A Neural-Network-Based Convex Regularizer for Image Reconstruction

The emergence of deep-learning-based methods for solving inverse problem...

0 Alexis Goujon, et al. ∙

research

∙ 11/11/2022

Self-Supervised Isotropic Superresolution Fetal Brain MRI

Superresolution T2-weighted fetal-brain magnetic-resonance imaging (FBMR...

0 Kay Lächler, et al. ∙

research

∙ 10/28/2022

Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions

Lipschitz-constrained neural networks have several advantages compared t...

0 Stanislas Ducotterd, et al. ∙

research

∙ 08/16/2022

Delaunay-Triangulation-Based Learning with Hessian Total-Variation Regularization

Regression is one of the core problems tackled in supervised learning. R...

0 Mehrsa Pourya, et al. ∙

research

∙ 06/29/2022

From Kernel Methods to Neural Networks: A Unifying Variational Formulation

The minimization of a data-fidelity term and an additive regularization ...

0 Michael Unser, et al. ∙

research

∙ 06/17/2022

The Role of Depth, Width, and Activation Complexity in the Number of Linear Regions of Neural Networks

Many feedforward neural networks generate continuous and piecewise-linea...

0 Alexis Goujon, et al. ∙

research

∙ 06/14/2022

Stability of image reconstruction algorithms

Robustness and stability of image reconstruction algorithms have recentl...

0 Pol del Aguila Pla, et al. ∙

research

∙ 06/07/2022

Asymptotic Stability in Reservoir Computing

Reservoir Computing is a class of Recurrent Neural Networks with interna...

0 Jonathan Dong, et al. ∙

research

∙ 04/28/2022

Bona fide Riesz projections for density estimation

The projection of sample measurements onto a reconstruction space repres...

0 P. del Aguila Pla, et al. ∙

research

∙ 04/13/2022

Approximation of Lipschitz Functions using Deep Spline Neural Networks

Lipschitz-constrained neural networks have many applications in machine ...

0 Sebastian Neumayer, et al. ∙

research

∙ 03/18/2022

Bayesian Inversion for Nonlinear Imaging Models using Deep Generative Priors

Most modern imaging systems involve a computational reconstruction pipel...

0 Pakshal Bohra, et al. ∙

research

∙ 03/10/2022

Stable Parametrization of Continuous and Piecewise-Linear Functions

Rectified-linear-unit (ReLU) neural networks, which play a prominent rol...

0 Alexis Goujon, et al. ∙

research

∙ 03/04/2022

Ridges, Neural Networks, and the Radon Transform

A ridge is a function that is characterized by a one-dimensional profile...

0 Michael Unser, et al. ∙

research

∙ 12/27/2021

Sparsest Univariate Learning Models Under Lipschitz Constraint

Beside the minimization of the prediction error, two of the most desirab...

0 Shayan Aziznejad, et al. ∙

research

∙ 12/12/2021

Measuring Complexity of Learning Schemes Using Hessian-Schatten Total-Variation

In this paper, we introduce the Hessian-Schatten total-variation (HTV) –...

0 Shayan Aziznejad, et al. ∙

research

∙ 12/16/2020

Shortest Multi-Spline Bases for Generalized Sampling

Generalized sampling consists in the recovery of a function f, from the ...

0 Alexis Goujon, et al. ∙

research

∙ 10/26/2020

Optimal transport-based metric for SMLM

We propose the use of Flat Metric to assess the performance of reconstru...

0 Quentin Denoyelle, et al. ∙

research

∙ 09/24/2020

Robust Phase Unwrapping via Deep Image Prior for Quantitative Phase Imaging

Quantitative phase imaging (QPI) is an emerging label-free technique tha...

0 Fangshu Yang, et al. ∙

research

∙ 08/07/2020

Generating Sparse Stochastic Processes Using Matched Splines

We provide an algorithm to generate trajectories of sparse stochastic pr...

0 Leello Dadi, et al. ∙

research

∙ 01/17/2020

Deep Neural Networks with Trainable Activations and Controlled Lipschitz Constant

We introduce a variational framework to learn the activation functions o...

0 Shayan Aziznejad, et al. ∙

research

∙ 10/03/2019

Time-Dependent Deep Image Prior for Dynamic MRI

We propose a novel unsupervised deep-learning-based algorithm to solve t...

18 Kyong Hwan Jin, et al. ∙

research

∙ 04/24/2019

Native Banach spaces for splines and variational inverse problems

We propose a systematic construction of native Banach spaces for general...

0 Michael Unser, et al. ∙

research

∙ 03/02/2019

A unifying representer theorem for inverse problems and machine learning

The standard approach for dealing with the ill-posedness of the training...

0 Michael Unser, et al. ∙

research

∙ 01/14/2019

Self-Supervised Deep Active Accelerated MRI

We propose to simultaneously learn to sample and reconstruct magnetic re...

14 Kyong Hwan Jin, et al. ∙

research

∙ 12/19/2018

Pocket Guide to Solve Inverse Problems with GlobalBioIm

GlobalBioIm is an open-source MATLAB library for solving inverse problem...

0 Emmanuel Soubies, et al. ∙

research

∙ 11/02/2018

An L1 Representer Theorem for Multiple-Kernel Regression

The theory of RKHS provides an elegant framework for supervised learning...

0 Shayan Aziznejad, et al. ∙

research

∙ 10/23/2018

Principled Design and Implementation of Steerable Detectors

We provide a complete pipeline for the detection of patterns of interest...

0 Julien Fageot, et al. ∙

research

∙ 09/19/2018

Direct Reconstruction of Saturated Samples in Band-Limited OFDM Signals

Given a set of samples, a few of them being possibly saturated, we propo...

0 Kyong Hwan Jin, et al. ∙

research

∙ 06/12/2018

Fast Rotational Sparse Coding

We propose an algorithm for rotational sparse coding along with an effic...

2 Michael T. McCann, et al. ∙

research

∙ 03/15/2018

Diverse M-Best Solutions by Dynamic Programming

Many computer vision pipelines involve dynamic programming primitives su...

0 Carsten Haubold, et al. ∙

research

∙ 02/26/2018

A representer theorem for deep neural networks

We propose to optimize the activation functions of a deep neural network...

0 Michael Unser, et al. ∙

research

∙ 02/06/2018

Fast Piecewise-Affine Motion Estimation Without Segmentation

Current algorithmic approaches for piecewise affine motion estimation ar...

0 Denis Fortun, et al. ∙

research

∙ 02/05/2018

Continuous-Domain Solutions of Linear Inverse Problems with Tikhonov vs. Generalized TV Regularization

We consider linear inverse problems that are formulated in the continuou...

0 Harshit Gupta, et al. ∙

research

∙ 09/06/2017

CNN-Based Projected Gradient Descent for Consistent Image Reconstruction

We present a new method for image reconstruction which replaces the proj...

0 Harshit Gupta, et al. ∙

research

∙ 07/11/2017

Efficient Inversion of Multiple-Scattering Model for Optical Diffraction Tomography

Optical diffraction tomography relies on solving an inverse scattering p...

0 Emmanuel Soubies, et al. ∙

research

∙ 05/16/2017

Learning Convex Regularizers for Optimal Bayesian Denoising

We propose a data-driven algorithm for the maximum a posteriori (MAP) es...

0 Ha Q. Nguyen, et al. ∙

research

∙ 11/11/2016

Deep Convolutional Neural Network for Inverse Problems in Imaging

In this paper, we propose a novel deep convolutional neural network (CNN...

0 Kyong Hwan Jin, et al. ∙

research

∙ 12/07/2015

On The Continuous Steering of the Scale of Tight Wavelet Frames

In analogy with steerable wavelets, we present a general construction of...

0 Zsuzsanna Püspöki, et al. ∙

research

∙ 09/14/2012

Hessian Schatten-Norm Regularization for Linear Inverse Problems

We introduce a novel family of invariant, convex, and non-quadratic func...

0 Stamatios Lefkimmiatis, et al. ∙

research

∙ 07/22/2011

On the Hilbert transform of wavelets

A wavelet is a localized function having a prescribed number of vanishin...

0 Kunal Narayan Chaudhury, et al. ∙

research

∙ 05/21/2011

Fast O(1) bilateral filtering using trigonometric range kernels

It is well-known that spatial averaging can be realized (in space or fre...

0 Kunal Narayan Chaudhury, et al. ∙

research

∙ 03/10/2010

Fast space-variant elliptical filtering using box splines

The efficient realization of linear space-variant (non-convolution) filt...

0 Kunal Narayan Chaudhury, et al. ∙

research

∙ 08/26/2009

Fast adaptive elliptical filtering using box splines

We demonstrate that it is possible to filter an image with an elliptic w...

0 Kunal Narayan Chaudhury, et al. ∙

research

∙ 08/26/2009

Gabor wavelet analysis and the fractional Hilbert transform

We propose an amplitude-phase representation of the dual-tree complex wa...

0 Kunal Narayan Chaudhury, et al. ∙

research

∙ 08/24/2009

Construction of Hilbert Transform Pairs of Wavelet Bases and Gabor-like Transforms

We propose a novel method for constructing Hilbert transform (HT) pairs ...

0 Kunal Narayan Chaudhury, et al. ∙

research

∙ 08/24/2009

On the Shiftability of Dual-Tree Complex Wavelet Transforms

The dual-tree complex wavelet transform (DT-CWT) is known to exhibit bet...

0 Kunal Narayan Chaudhury, et al. ∙

Michael Unser

Featured Co-authors