Thomas Pock
YOU?
Author Swipe
View article: An Inertial Langevin Algorithm
An Inertial Langevin Algorithm Open
We present a novel method for drawing samples from Gibbs distributions with densities of the form $π(x) \propto \exp(-U(x))$. The method accelerates the unadjusted Langevin algorithm by introducing an inertia term similar to Polyak's heavy…
View article: An Adaptively Inexact Method for Bilevel Learning Using Primal–Dual-Style Differentiation
An Adaptively Inexact Method for Bilevel Learning Using Primal–Dual-Style Differentiation Open
We consider a bilevel learning framework for learning linear operators. In this framework, the learnable parameters are optimized via a loss function that also depends on the minimizer of a convex optimization problem (denoted lower-level …
View article: ELEN – Predicting Loop Quality in Protein Structure Models
ELEN – Predicting Loop Quality in Protein Structure Models Open
1. Abstract Typically, sequences designed de novo are assessed in silico using deep learning-based protein structure prediction methods prior to wetlab testing. While these deep learning (DL) models excel at predicting well-ordered regions…
View article: Energy-based models for inverse imaging problems
Energy-based models for inverse imaging problems Open
In this chapter we provide a thorough overview of the use of energy-based models (EBMs) in the context of inverse imaging problems. EBMs are probability distributions modeled via Gibbs densities $p(x) \propto \exp{-E(x)}$ with an appropria…
View article: The Gaussian Latent Machine: Efficient Prior and Posterior Sampling for Inverse Problems
The Gaussian Latent Machine: Efficient Prior and Posterior Sampling for Inverse Problems Open
We consider the problem of sampling from a product-of-experts-type model that encompasses many standard prior and posterior distributions commonly found in Bayesian imaging. We show that this model can be easily lifted into a novel latent …
View article: Total Variation-Based Image Decomposition and Denoising for Microscopy Images
Total Variation-Based Image Decomposition and Denoising for Microscopy Images Open
Experimentally acquired microscopy images are unavoidably affected by the presence of noise and other unwanted signals, which degrade their quality and might hide relevant features. With the recent increase in image acquisition rate, moder…
View article: Machine-learning guided differentiation between photoplethysmography waveforms of supraventricular and ventricular origin
Machine-learning guided differentiation between photoplethysmography waveforms of supraventricular and ventricular origin Open
A neural network trained on ground truth PPG data collected during EP studies could distinguish between supraventricular or ventricular origin from PPG waveforms alone.
View article: Diffusion at Absolute Zero: Langevin Sampling using Successive Moreau Envelopes [journal paper]
Diffusion at Absolute Zero: Langevin Sampling using Successive Moreau Envelopes [journal paper] Open
We propose a method for sampling from Gibbs distributions of the form $π(x)\propto\exp(-U(x))$ by considering a family $(π^{t})_t$ of approximations of the target density which is such that $π^{t}$ exhibits favorable properties for samplin…
View article: FlowSDF: Flow Matching for Medical Image Segmentation Using Distance Transforms
FlowSDF: Flow Matching for Medical Image Segmentation Using Distance Transforms Open
Medical image segmentation plays an important role in accurately identifying and isolating regions of interest within medical images. Generative approaches are particularly effective in modeling the statistical properties of segmentation m…
View article: Diffusion at Absolute Zero: Langevin Sampling Using Successive Moreau Envelopes [conference paper]
Diffusion at Absolute Zero: Langevin Sampling Using Successive Moreau Envelopes [conference paper] Open
In this article we propose a novel method for sampling from Gibbs distributions of the form $π(x)\propto\exp(-U(x))$ with a potential $U(x)$. In particular, inspired by diffusion models we propose to consider a sequence $(π^{t_k})_k$ of ap…
View article: Product of Gaussian Mixture Diffusion Model for non-linear MRI Inversion
Product of Gaussian Mixture Diffusion Model for non-linear MRI Inversion Open
Diffusion models have recently shown remarkable results in magnetic resonance imaging reconstruction. However, the employed networks typically are black-box estimators of the (smoothed) prior score with tens of millions of parameters, rest…
View article: An Adaptively Inexact Method for Bilevel Learning Using Primal-Dual Style Differentiation
An Adaptively Inexact Method for Bilevel Learning Using Primal-Dual Style Differentiation Open
We consider a bilevel learning framework for learning linear operators. In this framework, the learnable parameters are optimized via a loss function that also depends on the minimizer of a convex optimization problem (denoted lower-level …
View article: FlowSDF: Flow Matching for Medical Image Segmentation Using Distance Transforms
FlowSDF: Flow Matching for Medical Image Segmentation Using Distance Transforms Open
Medical image segmentation plays an important role in accurately identifying and isolating regions of interest within medical images. Generative approaches are particularly effective in modeling the statistical properties of segmentation m…
View article: Machine-learning guided differentiation between photoplethysmography waveforms of supraventricular and ventricular origin
Machine-learning guided differentiation between photoplethysmography waveforms of supraventricular and ventricular origin Open
Aims To test, whether a neural network-based classifier could aid in distinguishing photoplethysmographic (PPG) pulse waveforms of ventricular from those of supraventricular origin. Methods Thirty patients undergoing invasive electrophysio…
View article: Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition
Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition Open
Concerns for the privacy of individuals captured in public imagery have led to privacy-preserving action recognition. Existing approaches often suffer from issues arising through obfuscation being applied globally and a lack of interpretab…
View article: Product of Gaussian Mixture Diffusion Models
Product of Gaussian Mixture Diffusion Models Open
In this work, we tackle the problem of estimating the density $$ f_X $$ of a random variable $$ X $$ by successive smoothing, such that the smoothed random variable $$ Y $$ fulfills the diffusion partial differential equation $$ (\parti…
View article: Utilization of deep learning tools to map and monitor biological soil crusts
Utilization of deep learning tools to map and monitor biological soil crusts Open
Biological soil crusts (biocrusts) form a layer of only one to few centimeters depth on the soil surface and occur mostly in hot and cold deserts. Biocrusts have a major impact on different processes in these ecosystems, like carbon and ni…
View article: Diffusion-based generation of Histopathological Whole Slide Images at a Gigapixel scale
Diffusion-based generation of Histopathological Whole Slide Images at a Gigapixel scale Open
We present a novel diffusion-based approach to generate synthetic histopathological Whole Slide Images (WSIs) at an unprecedented gigapixel scale. Synthetic WSIs have many potential applications: They can augment training datasets to enhan…
View article: Product of Gaussian Mixture Diffusion Models
Product of Gaussian Mixture Diffusion Models Open
In this work we tackle the problem of estimating the density $ f_X $ of a random variable $ X $ by successive smoothing, such that the smoothed random variable $ Y $ fulfills the diffusion partial differential equation $ (\partial_t - Δ_1)…
View article: Stable Deep MRI Reconstruction Using Generative Priors
Stable Deep MRI Reconstruction Using Generative Priors Open
Data-driven approaches recently achieved remarkable success in magnetic resonance imaging (MRI) reconstruction, but integration into clinical routine remains challenging due to a lack of generalizability and interpretability. In this paper…
View article: Subgradient Langevin Methods for Sampling from Non-smooth Potentials
Subgradient Langevin Methods for Sampling from Non-smooth Potentials Open
This paper is concerned with sampling from probability distributions $π$ on $\mathbb{R}^d$ admitting a density of the form $π(x) \propto e^{-U(x)}$, where $U(x)=F(x)+G(Kx)$ with $K$ being a linear operator and $G$ being non-differentiable.…
View article: On the Relationship Between RNN Hidden State Vectors and Semantic Ground Truth
On the Relationship Between RNN Hidden State Vectors and Semantic Ground Truth Open
We examine the assumption that the hidden-state vectors of recurrent neural networks (RNNs) tend to form clusters of semantically similar vectors, which we dub the clustering hypothesis. While this hypothesis has been assumed in the analys…
View article: Non-Log-Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithms
Non-Log-Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithms Open
We study the problem of approximate sampling from non-log-concave distributions, e.g., Gaussian mixtures, which is often challenging even in low dimensions due to their multimodality. We focus on performing this task via Markov chain Monte…