activity
20242026
collaborators

8 papers

cs.CV2026

Product-of-Gaussian-Mixture Diffusion Models for Joint Nonlinear MRI Reconstruction

Laurenz Nagler, Martin Zach, Thomas Pock

Recently, diffusion models have attracted considerable attention for magnetic resonance image reconstruction due to their high sample quality. However, most existing methods rely o…

math.NA2026

Forward-KL Convergence of Time-Inhomogeneous Langevin Diffusions

Andreas Habring, Martin Zach

Many practical samplers rely on time-dependent drifts -- often induced by annealing or tempering schedules -- to improve exploration and stability. This motivates a unified non-asy…

eess.IV2026

The Gaussian Latent Machine: Efficient Prior and Posterior Sampling for Inverse Problems

Muhamed Kuric, Martin Zach, Andreas Habring +2

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 sho…

math.OC2025

Computation of a Consistent System Matrix for Cone-beam Computed Tomography

Josef Simbrunner, Clemens Krenn, Martin Zach +1

We propose a method for the computation of a consistent system matrix for two- and three-dimensional cone-beam computed tomography (CT). The method relies on the decomposition of t…

eess.SP2025

A Statistical Benchmark for Diffusion Posterior Sampling Algorithms

Martin Zach, Youssef Haouchat, Michael Unser

We propose a statistical benchmark for diffusion posterior sampling (DPS) algorithms for Bayesian linear inverse problems. The benchmark synthesizes signals from sparse Lévy-proce…

eess.IV2025

Energy-based models for inverse imaging problems

Andreas Habring, Martin Holler, Thomas Pock +1

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 G…