I am a Ph.D. student at TUM's Computer Vision Group, headed by Prof. Dr. Daniel Cremers. My current research focuses on improving monocular 3D reconstruction and localization accuracy and efficiency.

Before joining the Ph.D. program, I worked as a Machine Learning Engineer at Knowlix GmbH. There, I researched OCR modeling and LLMs such as GPTs and Llama. I also designed data and machine learning pipelines and applied machine learning techniques to solve real-world problems.

I completed my Master's studies in Electrical Engineering and Information Technology at TUM. My focus was on Automation, Robotics, and AI. I spent a semester abroad at NTU Singapore, where I studied Deep Learning for Natural Language Processing and Genetic Algorithms.

For my Master's thesis, I worked at BMW Group AG on AR glasses and head 6DoF pose estimation based on 3D multi-view geometry reconstruction and deep learning. My research involved implementing a system that could estimate the head and AR glasses pose with high accuracy (Project). It resulted in a publication titled "Comparing Head and AR Glasses Pose Estimation."

I also completed my Bachelor of Science in Electrical Engineering and Information Technology at TUM, with a focus on Signal Processing. During my Bachelor's thesis, I worked on generative modeling using Capsule Generative Adversarial Networks at the Chair of Robotics, Artificial Intelligence, and Real-time Systems at TUM.

• Large-Scale Scene Reconstruction
• Visual Odometry
• Simultaneous Localization and Mapping
• Camera Relocalization
• Geospatial AI: Remote Sensing, Photogrammetry, Terrain Modeling, GIS

Update 07.2025 All student project positions are filled.

Successfully Finished Student Projects:

• Guided Research - Jingchao Xie: Uncertainty-VO: Improving End-to-End Self-Supervised Monocular Visual Odometry with Robust Projected Uncertainty
• Master Thesis - Robin Hanik: 6 DoF UAV Localization Using DOPs and DSMs under Varied Environmental Conditions
• Bachelor Thesis - Mohamed Skandrani: Exploring Gaussian Splatting for Enhanced 3D Reconstruction from Drone Imagery
• Master Thesis - Yue Tan: 3D Reconstruction of Street View Scenarios Using a Single Monocular Camera

Export as PDF, XML, TEX or BIB

Conference and Workshop Papers
2026
[]		IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection (J Meier, F Günther, R Marin, O Dhaouadi, J Kaiser and D Cremers), In IEEE Winter Conference on Applications of Computer Vision (WACV), 2026.  [bibtex] [arXiv:2511.19301]
[]		GrounDiff: Diffusion-Based Ground Surface Generation from Digital Surface Models (O Dhaouadi, J Meier, J Kaiser and D Cremers), In IEEE Winter Conference on Applications of Computer Vision (WACV), 2026. ([project page]) [bibtex] [pdf] [arXiv:2511.10391]
2025
[]		LeAD-M3D: Leveraging Asymmetric Distillation for Real-time Monocular 3D Detection (J Meier, J Michel, O Dhaouadi, YH Yang, C Reich, Z Bauer, S Roth, M Pollefeys, J Kaiser and D Cremers), In arXiv, 2025. ([project page]) [bibtex] [arXiv:2512.05663]
[]		OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata (O Dhaouadi, R Marin, J Meier, J Kaiser and D Cremers), In 39th Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2025. ([project page]) [bibtex] [pdf] [arXiv:2509.18350]Oral Presentation
[]		CoProU-VO: Combining Projected Uncertainty for End-to-End Unsupervised Monocular Visual Odometry (J* Xie, O* Dhaouadi, W Chen, J Meier, J Kaiser and D Cremers), In 47th German Conference on Pattern Recognition (GCPR), 2025. ([project page]) [bibtex] [pdf] [arXiv:2508.00568]Oral Presentation - Best Paper Award
[]		Shape Your Ground: Refining Road Surfaces Beyond Planar Representations (O Dhaouadi, J Meier, J Kaiser and D Cremers), In IEEE Intelligent Vehicles Symposium, 2025. ([project page]) [bibtex] [pdf] [doi]
[]		Highly Accurate and Diverse Traffic Data: The DeepScenario Open 3D Dataset (O* Dhaouadi, J* Meier, L Wahl, J Kaiser, L Scalerandi, N Wandelburg, Z Zhuo, N Berinpanathan, H Banzhaf and D Cremers), In IEEE Intelligent Vehicles Symposium, 2025. ([project page]) [bibtex] [pdf] [doi]
[]		MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models (JM Meier, L Inchingolo, O Dhaouadi, Y Xia, J Kaiser and D Cremers), In International Conference on Robotics and Automation (ICRA), 2025.  [bibtex] [pdf]Oral Presentation
[]		TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenes (Y Xia, Y Lu, R Song, O Dhaouadi, JF Henriques and D Cremers), In IEEE International Conference on Computer Vision (ICCV), 2025. ([project page]) [bibtex] [pdf]
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] [pdf]Oral Presentation
2021
[]		Comparing Head and AR Glasses Pose Estimation (A Firintepe, O Dhaouadi, A Pagani and D Stricker), In 2021 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), volume , 2021.  [bibtex] [pdf] [doi]