2026 Thomas Pock: Computer Science Researcher – H-Index, Publications & Awards

Discipline name	D-Index	World Ranking	Current World Ranking	National Ranking	Current National Ranking	Publications	Citations
Computer Science	71	1738	1684	12	11	241	28945

Overview

Thomas Pock is affiliated with Graz University of Technology in Austria and has made substantial contributions across several interrelated fields. Their research primarily spans computer science, medicine, and engineering, with a focus on advanced computational methods applied to medical imaging and image processing.

Their work encompasses key subfields such as computer vision and pattern recognition, radiology, nuclear medicine and imaging, artificial intelligence, cardiology and cardiovascular medicine, and computational mechanics. The integration of these areas reflects a multidisciplinary approach to medical technology and imaging sciences.

Main topics addressed in their research include sparse and compressive sensing techniques, medical image segmentation techniques, medical imaging techniques and applications, image and signal denoising methods, advanced MRI techniques and applications, advanced vision and imaging, and advanced image processing techniques.

Their publication record is extensive, with a notable presence in various academic venues. Frequent publication venues include:

arXiv (Cornell University)
Journal of Mathematical Imaging and Vision
SIAM Journal on Imaging Sciences
SIAM Journal on Mathematics of Data Science
IEEE Signal Processing Magazine

Their recent papers illustrate a strong emphasis on deep learning and variational methods applied to MRI reconstruction and cardiac electrophysiology modelling. Selected recent publications include:

"Deep-Learning Methods for Parallel Magnetic Resonance Imaging Reconstruction: A Survey of the Current Approaches, Trends, and Issues" (2020), published in IEEE Signal Processing Magazine
"A Framework for the generation of digital twins of cardiac electrophysiology from clinical 12-leads ECGs" (2021), published in Medical Image Analysis
"Deep Learning Reconstruction Enables Prospectively Accelerated Clinical Knee MRI" (2023), published in Radiology
"Bayesian Uncertainty Estimation of Learned Variational MRI Reconstruction" (2021), published in IEEE Transactions on Medical Imaging
"Variational Networks: An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration" (2020), published in Journal of Mathematical Imaging and Vision

Thomas Pock has collaborated frequently with several researchers, reflecting a network of co-authors contributing to his research domains. Among the most frequent co-authors are Erich Kobler, Alexander Effland, Gernot Plank, Martin Zach, and Antonin Chambolle.

Best Publications

A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging

Antonin Chambolle;Thomas Pock

5138
Citations
A duality based approach for realtime TV-L 1 optical flow

C. Zach;T. Pock;H. Bischof

2117
Citations
Total Generalized Variation

Kristian Bredies;Karl Kunisch;Thomas Pock

1761
Citations
Learning a variational network for reconstruction of accelerated MRI data.

Kerstin Hammernik;Teresa Klatzer;Erich Kobler;Michael P. Recht

1708
Citations
Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration

Yunjin Chen;Thomas Pock

1427
Citations
Second order total generalized variation (TGV) for MRI

Florian Knoll;Kristian Bredies;Thomas Pock;Rudolf Stollberger

696
Citations
An Improved Algorithm for TV-L1 Optical Flow

Andreas Wedel;Thomas Pock;Christopher Zach;Horst Bischof

612
Citations
An introduction to Total Variation for Image Analysis

Antonin Chambolle;Vicent Caselles;Matteo Novaga;Daniel Cremers

572
Citations
Anisotropic Huber-L1 Optical Flow

Manuel Werlberger;Werner Trobin;Thomas Pock;Andreas Wedel

539
Citations
Diagonal preconditioning for first order primal-dual algorithms in convex optimization

Thomas Pock;Antonin Chambolle

535
Citations
An introduction to continuous optimization for imaging

Antonin Chambolle;Thomas Pock

533
Citations
PROST: Parallel robust online simple tracking

Jakob Santner;Christian Leistner;Amir Saffari;Thomas Pock

518
Citations
iPiano: Inertial Proximal Algorithm for Nonconvex Optimization

Peter Ochs;Yunjin Chen;Thomas Brox;Thomas Pock

509
Citations
An algorithm for minimizing the Mumford-Shah functional

Thomas Pock;Daniel Cremers;Horst Bischof;Antonin Chambolle

466
Citations
On the ergodic convergence rates of a first-order primal---dual algorithm

Antonin Chambolle;Thomas Pock

462
Citations
An Inertial Forward-Backward Algorithm for Monotone Inclusions

Dirk A. Lorenz;Thomas Pock

460
Citations
On learning optimized reaction diffusion processes for effective image restoration

Yunjin Chen;Wei Yu;Thomas Pock

395
Citations
A Globally Optimal Algorithm for Robust TV-L 1 Range Image Integration

C. Zach;T. Pock;H. Bischof

335
Citations
Deep-Learning Methods for Parallel Magnetic Resonance Imaging Reconstruction: A Survey of the Current Approaches, Trends, and Issues

Florian Knoll;Kerstin Hammernik;Chi Zhang;Steen Moeller

331
Citations
A convex relaxation approach for computing minimal partitions

Thomas Pock;Antonin Chambolle;Daniel Cremers;Horst Bischof

322
Citations
iPiano: Inertial Proximal Algorithm for Non-Convex Optimization

Peter Ochs;Yunjin Chen;Thomas Brox;Thomas Pock

16
Citations

Frequent Co-Authors

Horst Bischof Graz University of Technology

Florian Knoll University of Erlangen-Nuremberg

Daniel Cremers Technical University of Munich

Rene Ranftl Intel (United States)

Daniel K. Sodickson New York University

Thomas Brox University of Freiburg

Konrad Schindler ETH Zurich

Karl Kunisch University of Graz

Martin Urschler University of Auckland

Gernot Plank Medical University of Graz

External Links

Personal website of Thomas Pock Google Scholar page

If you think any of the details on this page are incorrect, let us know.

Related Online Degrees & Career Pathways

Exploring academic pathways in Computer Science can open the door to various careers in tech, data analysis, and leadership. Many students opt for flexible study options, such as cheap online masters programs, which provide advanced training without the high cost of traditional degrees. These programs are ideal for working professionals aiming to boost their expertise without pausing their careers.

If you’re interested in leadership roles, consider pursuing an online doctorate leadership degree. This path helps graduates qualify for executive positions by developing advanced organizational and strategic skills. Another practical entry point is enrolling in community colleges near me, allowing you to start your journey in tech affordably before transferring to a four-year university.

For educators or those interested in academic leadership, the cheapest doctorate of education online can be an effective way to advance your credentials. No matter your starting point, affordable online programs make it easier than ever to access a range of degrees and career pathways in computer science and related fields.