Picture of Stefan Hörmann

Stefan Hörmann, M.Sc.

Technical University of Munich

Chair of Human-Machine Communication (Prof. Rigoll)

Postal address

Arcisstr. 21
80333 München

Research Areas

•  Deep Learning
•  Computer Vision
•  Face Recognition


  • Hörmann, S.; Knoche, M.; Rigoll, G.: A Multi-Task Comparator Framework for Kinship Verification. 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020) , 2020, pp. 665-669 more…
  • Hörmann, S.; Moiz, A.; Knoche, M.; Rigoll, G.: Attention Fusion for Audio-Visual Person Verification Using Multi-Scale Features. 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), 2020, pp. 472-476 more…
  • Hörmann, S.; Knoche, M.; Babaee, Ma.; Köpüklü, O.; Rigoll, G.: Outlier-Robust Neural Aggregation Network for Video Face Identification. Proc. International Conference on Image Processing (ICIP 2019), 2019, pp. 1675-1679 more… Full text ( DOI )
  • Babaee, Ma.; Zhu, Y.; Köpüklü, O.; Hörmann, S.; Rigoll, G.: Gait Energy Image Restoration Using Generative Adversarial Networks. Proc. International Conference on Image Processing (ICIP 2019), 2019, pp. 2596-2600 more… Full text ( DOI )
  • Köpüklü, O.; Babaee, Ma.; Hörmann, S.; Rigoll, G.: Convolutional Neural Networks with Layer Reuse. Proc. 26th IEEE International Conference on Image Processing (ICIP 2019), 2019, pp. 345-349 more… Full text ( DOI ) Full text (mediaTUM)
  • Hörmann, S.; Comulada Simpson, E.; Bahram, M.: A generic Steering Wheel Torque Model using Neural Networks. Proc. Driving Simulation Conference, 2017, 2017, pp. 43-50 more…

Conference Review Activities



Data-driven utilization of Multimedia Content
Partners: ProSiebenSat.1 Media SE, munich media intelligence
Period: 01.04.2017 - 30.09.2018


Signaltheorie (WS 2019)
Signal Represenation TUMAsia (WS 2019)
Signaldarstellung Übung für Wiederholer (SS 2019, SS 2018)
Signaldarstellung für MSE (WS 2018)
Signaldarstellung (WS 2018, WS 2017)

Student projects

For inquiries regarding any student projects please apply using your most recent CV together with your grade report emphasizing your previous experience in this area and your desired starting date.

Open Topics

You can find all open topics here.

Finished Projects

• Automotive Powertrain Health Prediction based on Diagnostic Trouble Code (Master's Thesis)
• Conditional Face Image Generation and Its Application in 3d Pedestrian Modelling (Master's Thesis)
• Different Effects of Quantization Methods on Convolutional Neural Networks (Research Internship)
• Efficient Multi-Currency Banknotes Classification Using Binarized Neural Networks (Bachelor's Thesis)
• An Image Aggregation Network for Video Face Recognition (Master's Thesis)
• Influence of Data Augmentation and Pose Variations on Face Recognition (Research Internship)

• Evaluation of Different Face Alignment Strategies for Face Identification (Research Internship)
• Dynamic Feature Learning for Partial Face Recognition (Scientific Seminar)
• A Survey on Set-Based Face Recognition (Research Internship)
• Attention Based Fusion Using Feature Aggregation for Audio-Visual Person Verification (Master's Thesis)
• Enhanced Driver Gaze Classification using Video Data together with Car Bus Signals (Master's Thesis)
• Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks (Scientific Seminar)
• Multicolumn Networks for Face Recognition (Scientific Seminar)
• Semi-automatic dataset labeling using pretrained neural networks (Research Internship)
• Facial Emotion Recognition for Automotive Applications using RGB-D Information (Master's Thesis)
• Gesichtsbasierte Schauspielererkennung in Filmen (Bachelor's Thesis)
• Comparison of different GANs for Face Recognition (Research Internship)
• Performance Evaluation of GANs for Face Recognition Tasks against Image Degradations (Master's Thesis)

• Exploring Disentangled Feature Representation Beyond Face Identification (Scientific Seminar)
• Seeing Voices and Hearing Faces: Cross-modal biometric matching (Scientific Seminar)
• Facelet-Bank for Fast Portrait Manipulation (Scientific Seminar)
• Joint Identification and Outlier Detection of Face Clusters Using an Aggregation Network (Master's Thesis)
• Region-based face detection with a fully-convolutional neural network (Master's Thesis)
• Disentangled Representation Learning GAN for Pose-Invariant Face Recognition (Scientific Seminar)
• Class Rectification Hard Mining for Imbalanced Deep Learning (Scientific Seminar)

• Detecting Masked Faces in the Wild with LLE-CNNs (Scientific Seminar)
• Finding Tiny Faces (Scientific Seminar)