Search Results for author:
Found 22 papers, 12 papers with code
Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching
In inverse problems, many conditional generative models approximate the posterior measure by minimizing a distance between the joint measure and its learned approximation.
Transfer Operators from Batches of Unpaired Points via Entropic Transport Kernels
In this paper, we are concerned with estimating the joint probability of random variables $X$ and $Y$, given $N$ independent observation blocks $(\boldsymbol{x}^i,\boldsymbol{y}^i)$, $i=1,\ldots, N$, each of $M$ samples $(\boldsymbol{x}^i,\boldsymbol{y}^i) = \bigl((x^i_j, y^i_{\sigma^i(j)}) \bigr)_{j=1}^M$, where $\sigma^i$ denotes an unknown permutation of i. i. d.
Wasserstein Gradient Flows for Moreau Envelopes of f-Divergences in Reproducing Kernel Hilbert Spaces
In this paper, we use the so-called kernel mean embedding to show that the corresponding regularization can be rewritten as the Moreau envelope of some function in the reproducing kernel Hilbert space associated with $K$.
Mixed Noise and Posterior Estimation with Conditional DeepGEM
Motivated by indirect measurements and applications from nanometrology with a mixed noise model, we develop a novel algorithm for jointly estimating the posterior and the noise parameters in Bayesian inverse problems.
Manifold GCN: Diffusion-based Convolutional Neural Network for Manifold-valued Graphs
We propose two graph neural network layers for graphs with features in a Riemannian manifold.
Learning from small data sets: Patch-based regularizers in inverse problems for image reconstruction
The solution of inverse problems is of fundamental interest in medical and astronomical imaging, geophysics as well as engineering and life sciences.
Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
We propose conditional flows of the maximum mean discrepancy (MMD) with the negative distance kernel for posterior sampling and conditional generative modeling.
Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problems
Conditional generative models became a very powerful tool to sample from Bayesian inverse problem posteriors.
Multilevel Diffusion: Infinite Dimensional Score-Based Diffusion Models for Image Generation
We thereby intend to obtain diffusion models that generalize across different resolution levels and improve the efficiency of the training process.
Neural Wasserstein Gradient Flows for Maximum Mean Discrepancies with Riesz Kernels
Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals with non-smooth Riesz kernels show a rich structure as singular measures can become absolutely continuous ones and conversely.
PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization
Learning neural networks using only few available information is an important ongoing research topic with tremendous potential for applications.
Lagrangian Motion Magnification with Double Sparse Optical Flow Decomposition
In this paper, we propose a novel approach for local Lagrangian motion magnification of facial micro-motions.
Generalized Normalizing Flows via Markov Chains
Normalizing flows, diffusion normalizing flows and variational autoencoders are powerful generative models.
Stochastic Normalizing Flows for Inverse Problems: a Markov Chains Viewpoint
To overcome topological constraints and improve the expressiveness of normalizing flow architectures, Wu, K\"ohler and No\'e introduced stochastic normalizing flows which combine deterministic, learnable flow transformations with stochastic sampling methods.
Invertible Neural Networks versus MCMC for Posterior Reconstruction in Grazing Incidence X-Ray Fluorescence
Grazing incidence X-ray fluorescence is a non-destructive technique for analyzing the geometry and compositional parameters of nanostructures appearing e. g. in computer chips.
Super-Resolution for Doubly-Dispersive Channel Estimation
In this work we consider the problem of identification and reconstruction of doubly-dispersive channel operators which are given by finite linear combinations of time-frequency shifts.
Super-Resolution
Information Theory
Numerical Analysis
Information Theory
Numerical Analysis
47A62, 65R30, 65T99, 94A20
Convolutional Proximal Neural Networks and Plug-and-Play Algorithms
In this paper, we introduce convolutional proximal neural networks (cPNNs), which are by construction averaged operators.
PCA Reduced Gaussian Mixture Models with Applications in Superresolution
To learn the (low dimensional) parameters of the mixture model we propose an EM algorithm whose M-step requires the solution of constrained optimization problems.
Linkage between piecewise constant Mumford-Shah model and ROF model and its virtue in image segmentation
The piecewise constant Mumford-Shah (PCMS) model and the Rudin-Osher-Fatemi (ROF) model are two important variational models in image segmentation and image restoration, respectively.
A Nonlocal Denoising Algorithm for Manifold-Valued Images Using Second Order Statistics
This paper is the first attempt to generalize this technique to manifold-valued images.
A Second Order Non-Smooth Variational Model for Restoring Manifold-Valued Images
We introduce a new non-smooth variational model for the restoration of manifold-valued data which includes second order differences in the regularization term.
Numerical Analysis 65K10, 49Q99, 49M37
First order algorithms in variational image processing
Variational methods in imaging are nowadays developing towards a quite universal and flexible tool, allowing for highly successful approaches on tasks like denoising, deblurring, inpainting, segmentation, super-resolution, disparity, and optical flow estimation.
