Institut für Informationsverarbeitung (TNT)

Mathis Kruse studied computer science with a minor in mathematics at the Leibniz Universität Hannover and received his master’s degree in April 2023.

Since June 2023 he has been working towards his PhD at the Institute for Information Processing, focusing on anomaly detection.

Mathis Kruse, Melissa Schween, Bodo Rosenhahn
MATCH: Flow Matching for Multi-View Anomaly Detection
European Conference on Computer Vision (ECCV), September 2026
(arXiv.org, GitHub) BibTeX
Melissa Schween, Mathis Kruse, Bodo Rosenhahn
BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2026
(arXiv.org, GitHub) BibTeX
Mathis Kruse, Bodo Rosenhahn
Multi-Flow: Multi-View-Enriched Normalizing Flows for Industrial Anomaly Detection
Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops, pp. 3933--3944, June 2025
(arXiv.org, GitHub) BibTeX
Melanie Schaller, Mathis Kruse, Antonio Ortega, Marius Lindauer, Bodo Rosenhahn
AutoML for Multi-Class Anomaly Compensation of Sensor Drift
Measurement, 2025
(arXiv.org, GitHub) BibTeX
Mathis Kruse, Marco Rudolph, Dominik Woiwode, Bodo Rosenhahn
SplatPose & Detect: Pose-Agnostic 3D Anomaly Detection
IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 - Workshops, IEEE, pp. 3950--3960, June 2024
(arXiv.org, GitHub) BibTeX