Profile
|
M.Sc. Stephanie Käs |
Stephanie Käs
PhD Researcher - iBehave Excellence Network - Human Motion Understanding
ZONTA Women in STEM D29 Scholarship & Club Award Aachen - JSPS Fellow
News & Updates 2026
- Received the ZONTA Women in STEM Scholarship 2026 of District 29
- Talk accepted at the German Aerospace Congress (DLRK) 2026
- Full paper accepted at ESA's AI for space conference (SPAICE) 2026
- Admitted as Visiting Postgraduate Researcher to the University of Bristol (UK)
- Received a Scholarship by the Japanese Society for the Promotion of Science (JSPS) for research in Tokyo
- Received Aachen's ZONTA Women in STEM Award 2026
- Paper accepted at WACV 2026 Workshop
- Poster accepted at GRC 2026
About Me
I am an interdisciplinary PhD researcher focusing on human movement understanding in challenging real-world environments such as fisheye and space imagery. My work combines human pose estimation, gesture recognition, and large-scale foundation models to enable robust perception for human-robot interaction. I am grateful to work with national and international partners (Bosch Research, Uni Bristol, NII Tokyo). Recently, I have been initiating a new research collaboration on human perception in space environments with the German Aerospace Center (DLR).
I have supervised multiple Bachelor’s and Master’s theses and place strong emphasis on clear science communication.
Note: Thesis applications are closed until autumn. Please send your applications on human monitoring for space applications no earlier than October 2026.
Research Interests
- Human Pose Estimation & Motion Understanding
- Gesture & Action Recognition
- Human-Robot Interaction (HRI
- Humans in Space
- Foundation Models for Vision
- Fisheye & Omnidirectional Vision
Publications
-
Käs, S., Flaig, M., Woyke, L. et al.:
AstroPIE-53: Towards Understanding Failure Modes of Human Pose Estimation in Space, SPAICE (2026). -
Käs, S., Schönherr, E. et al.:
We Still See Broken Limbs: Towards Anatomical Realism in GenAI via Human Preference Learning., WACV Workshop (2026). -
Käs, S., Linder, T., Leibe, B.:
Human Gesture & Activity Recognition in Scene Context for Intralogistic Mobile Robots, GRC (2026). -
Käs, S., Burenko, A., Markert, L. et al.:
How do Foundation Models Compare to Skeleton-Based Approaches for Gesture Recognition in Human-Robot Interaction?, RO-MAN (2025). -
Käs, S., Peter, S., Thillmann, H. et al.:
Systematic Evaluation of Different Projection Methods for Monocular 3D Human Pose Estimation on Heavily Distorted Fisheye Images, ICRA (2025). -
Dort, K., Bilk, J., Käs, S. et al.:
Comparison of supervised and unsupervised anomaly detection in Belle II pixel detector data
Eur. Phys. J. C 82, 587 (2022).
Supervision & Mentoring
Current Students: O. A. Culha, M. Flaig, M. Sayegh, A. Weissberg, L. Woyke
Former Projects:
- M. Flaig: "Towards Fine-Grained Human Motion Descriptions" (B. Sc. Thesis, 05/25–09/25)
- B. Thal: "Comparison of Person De-Identification Methods in Human Pose Estimation" (B.Sc. Thesis, 05/25–09/25)
- E. Schönherr: "Anatomical Realism in AI-Generated Human Images" (M. Sc. Thesis, 09/25–11/25)
- L. Markert: "Gesture Recognition Using a Video Foundation Model" (B. Sc. Thesis, 09/24–03/25)
- S. Peter: Fisheye Human Pose Estimation (Intern, 11/23–10/24)
- H. Thillmann: "Re-Engineering an Absolute Pose Estimation Architecture: Enabling Extensibility via Modularization" (M. Sc. Thesis, 09/23–10/24)
- A. Burenko: "Stabilization, Tracking, and Gesture Recognition Methods within Skeleton-based Human Pose Estimation Framework" (M. Sc. Thesis, 09/23–09/24)
- V. Hilla: "An Analysis of Error Sources to Improve Temporal Consistency in 3D Human Pose Estimation" (M. Sc. Thesis, 09/23–07/24, Awarded as best thesis in Computer Science)
- T. Schellhaas: "Identifizierung von langsamen Pionen durch Support Vector Machines" (B. Sc. Thesis)
- Project Leader: "Stratospheric Balloon Research Project" "StratoGI" (JLU Gießen)
Teaching Experience
- Lectureship: Statistics for Geosciences (2022/23, JLU Gießen)
- Exercise Teaching Assistant: (Advanced) Machine Learning, Computer Vision (RWTH Aachen)
- Seminar Teaching Assistant: Historical & Current Milestones in Machine Learning and Computer Vision (RWTH Aachen)
- Lab Teaching Assistant: Experimental Physics Lab I–III (JLU Gießen)
Invited Talks & Outreach
- Invited Talk: Amazon Science 2026
- Invited Talk: Deutsches Museum München 2025
- Invited Talk: HASCO Summer School 2024 (University of Göttingen)
- Invited Talk: ErUM-Data-Hub 2023/24 (RWTH Aachen, TU Dresden)
- Guest Speaker: JLU Digitaltag 2024
- Invited Talk: Belle II Research Meeting 2022 (TUM)
- Public Speaker: Student Hybrid Rocket Team "HybridLaunch"
Publications
Systematic Evaluation of Different Projection Methods for Monocular 3D Human Pose Estimation on Heavily Distorted Fisheye Images
Authors: Stephanie Käs, Sven Peter, Henrik Thillmann, Anton Burenko, Timm Linder, David Adrian, and Dennis Mack, Bastian Leibe
In this work, we tackle the challenge of 3D human pose estimation in fisheye images, which is crucial for applications in robotics, human-robot interaction, and automotive perception. Fisheye cameras offer a wider field of view, but their distortions make pose estimation difficult. We systematically analyze how different camera models impact prediction accuracy and introduce a strategy to improve pose estimation across diverse viewing conditions.
A key contribution of our work is FISHnCHIPS, a novel dataset featuring 3D human skeleton annotations in fisheye images, including extreme close-ups, ground-mounted cameras, and wide-FOV human poses. To support future research, we will be publicly releasing this dataset.
More details coming soon — stay tuned for the final publication! Looking forward to sharing our findings at ICRA 2025!
