I received my M.Sc. in Computer Science from the University of Tuebingen. I did my master thesis with Bosch Research in Renningen and was supervised by Prof. Dr. Andreas Geiger and Dr. Wieland Brendel of the Max Planck Institute Tuebingen. I am a Ph.D. student in the Computer Vision Group, headed by Prof. Dr. Daniel Cremers at TUM. My research focuses on 3D object detection, tracking, semi-supervised learning and domain adaptation.

Are you excited about Computer Vision and Machine Learning? Are you interested in doing high impact work and submitting it to top conferences?

Then apply for one of the Master’s theses below.

I pursue publications in conferences like CVPR, ICCV, and ECCV and solve challenging computer vision problems identified jointly with Deepscenario - a highly innovative start-up in the automotive industry advised by Prof. Daniel Cremers (https://www.deepscenario.com/).

Specific thesis topics:

Master thesis: Domain Adaptation for Monocular 3D object detection  in Autonomous Driving

Monocular 3D object detection is a challenging task because it requires models to predict the location, dimensions, and rotation of objects from a single input image. Traditional autonomous driving datasets, such as KITTI, NuScenes, Waymo, and Rope3D, are captured from a car or traffic view perspective. However, this can limit the generalization ability of models trained on these datasets. For example, a model trained on data from a car view may not be able to accurately detect objects from a drone view. In this thesis we want to answer the following research question: How can we generalize monocular 3D object detection models from a set of training perspectives to an unseen perspective during inference? 

Master thesis: Generalized Monocular Depth Prediction for Autonomous Driving

Monocular depth prediction is a key challenge for autonomous driving. Current approaches either directly predict depth or use strong assumptions that require the input image to be taken from a specific perspective. This limits the generalization ability of these approaches to different perspectives. This thesis will investigate how to perform accurate depth prediction from any perspective, including car view, traffic view, and drone view.

Working with Johannes as a mentor during my Master's thesis was a great experience. Johannes proved to be an exceptional supervisor who is focused, dedicated and highly supportive. I benefited greatly from Johannes' extensive knowledge and insightful feedback on several occasions, which meaningfully impacted the quality and depth of my work. I would recommend Johannes for any future mentorship or professional role where his expertise and supportive approach would be an asset. (Luca Scalerandi, Master Thesis Student in 3D Tracking)

Working with Johannes was an invaluable opportunity that significantly enriched my experience. He consistently provided constructive feedback and technical support, enabling me to enhance my understanding and improve the quality of my work. Johannes is approachable, responsive, and always open to engaging in meaningful discussions. His supervision was both supportive and motivating, often involving hands-on collaboration to solve complex problems. His guidance not only elevated the quality of my research but also deepened my knowledge of the field. I wholeheartedly recommend Johannes as a supervisor. (Melih Görgülü, Master Thesis Student in Monocular 3D Detection)

Export as PDF, XML, TEX or BIB

Conference and Workshop Papers
2024
[]		CARLA Drone: Monocular 3D Object Detection from a Different Perspective (JM Meier, L Scalerandi, O Dhaouadi, J Kaiser, N Araslanov and D Cremers), In 46th German Conference on Pattern Recognition (GCPR), 2024. ([project page]) [bibtex]Oral Presentation
2023
[]		NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging (K Guirguis, J Meier, G Eskandar, M Kayser, B Yang and J Beyerer), In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.  [bibtex] [arXiv:2303.04958]
2021
[]		A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines (V Borisov, J Meier, Jvan den Heuvel, H Jalali and G Kasneci), In Neural Information Processing Systems Conference - NeurIPS 2021: eXplainable AI approaches for debugging and diagnosis workshop, 2021.  [bibtex] [arXiv:2111.07379]