Universität Ulm
Institute of Media Informatics
Visual Computing Group logo Visual Computing Group Ulm University

Tristan Payer has joined the Visual Computing Group in November 2020 and worked as research associate until May 2024.

He received his master’s degree in 2020 from Radboud University Nijmegen in the field of Artificial Intelligence. His focus in the master’s program was on Natural Language Processing, Medical Image Analysis and Deep Learning. Previously, he completed his bachelor’s degree at Radboud University Nijmegen in 2018.

Research interests

  • Image Segmentation
  • Semi-supervised learning

Theses

I’m currently mainly working on Deep Learning techniques for semantic Image Segmentation and semi-supervised learning.
I am interested in everything around those topics.

If you are interested in writing a thesis that fits in those topics, feel free to send me an email or come by my office.

Supervised Theses

2 theses
Master
Learning Occasion Recommendations for Design Elements Based on Photos
Pascal Hofstäter
2023
Bachelor
Domain specific augmentations in contrastive learning
Niklas Gund
2022

Publications

7 papers
A Survey on Quality Metrics for Text-to-Image Generation
A Survey on Quality Metrics for Text-to-Image Generation
Sebastian Hartwig, Leon Sick, Hannah Kniesel, Tristan Payer, Poonam Poonam, Michael Glöckler, Alex Bäuerle, Timo Ropinski
TVCG 2025 ↓PDF
DeepEM Playgound: Bringing Deep Learning to Electron Microscopy Labs
DeepEM Playgound: Bringing Deep Learning to Electron Microscopy Labs
Hannah Kniesel, Poonam Poonam, Tristan Payer, Tim Bergner, Pedro Hermosilla, Timo Ropinski
jmi 2025 ‹›Code
Less is More: Selective reduction of CT data for self-supervised pre-training of deep learning models with contrastive learning improves downstream classification performance
Less is More: Selective reduction of CT data for self-supervised pre-training of deep learning models with contrastive learning improves downstream classification performance
Daniel Wolf, Tristan Payer, Cathrina Silvia Lisson, Christoph Gerhard Lisson, Meinrad Beer, Michael Götz*, Timo Ropinski*
CIBM 2024 ↓PDF ‹›Code
Evaluating Text-to-Image Synthesis: Survey and Taxonomy of Image Quality Metrics
Evaluating Text-to-Image Synthesis: Survey and Taxonomy of Image Quality Metrics
Sebastian Hartwig, Dominik Engel, Leon Sick, Hannah Kniesel, Tristan Payer, Poonam Poonam, Michael Glöckler, Alex Bäuerle, Timo Ropinski
arXiv ↓PDF
Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images
Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images
Hannah Kniesel, Leon Sick, Tristan Payer, Tim Bergner, Kavitha Shaga Devan, Clarissa Read, Paul Walther, Timo Ropinski, Pedro Hermosilla
ICLR 2024 ↓PDF ‹›Code
Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical Imaging
Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical Imaging
Daniel Wolf, Tristan Payer, Cathrina Silvia Lisson, Christoph Gerhard Lisson, Meinrad Beer, Michael Götz*, Timo Ropinski*
Nature Scientific Reports 2023 ↓PDF ‹›Code
Medical volume segmentation by overfitting sparsely annotated data
Medical volume segmentation by overfitting sparsely annotated data
Tristan Payer, Faraz Nizamani, Meinrad Beer, Michael Götz, Timo Ropinski
SPIE JMI 2023 ↓PDF
← Back to Team