| Home

Hi! I am Sebastian Schmidt, a engineer and researcher working on machine learning research and application around emboddiment AI and their applications.

I am currently a Scientist and Engineer at BMW Group in autonomous driving and a Senior Research Associate at the Technical University of Munich (TUM) in the Data Analytics and Machine Learning (DAML) group.

Before this role, I was PhD studen at TUM under the supervision of Prof. Dr. Stephan Günnemann and a Research Scientist at BMW, leading and contributing to research on active learning, out-of-distribution detection, uncertainty estimation, and multimodal perception.

I was also a founding member of recoro.io, where I contributed build the startup from the ground up as part of the core team. I was deeply involved in shaping development and release processes, establishing cloud and CI/CD infrastructure, and the data pipeline as well as prototype and developing the product.

Earlier in my career, I worked as an engineer in BMW’s autonomous driving division, developing perception algorithms and scalable data and ML pipelines for large-scale deployment.

Across academia, startup, and industry, I enjoy building end-to-end systems from prototype to production and collaborating with interdisciplinary teams. I am always happy to connect with like-minded people in research and applied AI.

selected publications

Prior2Former - Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation

Sebastian Schmidt, Julius Körner, Dominik Fuchsgruber, and 3 more authors

In , 2025

Abs Bib PDF Website

@inproceedings{Schmidt2025b,
  title = {Prior2Former - Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation},
  author = {Schmidt, Sebastian and K\"orner, Julius and Fuchsgruber, Dominik and Gasperini, Stefano and Tombari, Federico and G\"unnemann, Stephan},
  year = {2025},
  journal = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) - Highlight},
  url = {http://arxiv.org/abs/2405.11337},
  volume = {2405.11337},
  eprint = {arXiv:2405.11337},
}

Joint Out-of-Distribution Filtering and Data Discovery Active Learning

Sebastian Schmidt, Leonard Schenk, Leo Schwinn, and 1 more author

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Abs Bib PDF Website

As the data demand for deep learning models increases, active learning (AL) becomes essential to strategically select samples for labeling, which maximizes data efficiency and reduces training costs. Real-world scenarios necessitate the consideration of incomplete data knowledge within AL. Prior works address handling out-of-distribution (OOD) data, while another research direction has focused on category discovery. However, a combined analysis of real-world considerations combining AL with out-of-distribution data and category discovery remains unexplored. To address this gap, we propose Joint Out-of-distribution filtering and data Discovery Active learning (Joda) , to uniquely address both challenges simultaneously by filtering out OOD data before selecting candidates for labeling. In contrast to previous methods, we deeply entangle the training procedure with filter and selection to construct a common feature space that aligns known and novel categories while separating OOD samples. Unlike previous works, Joda is highly efficient and completely omits auxiliary models and training access to the unlabeled pool for filtering or selection. In extensive experiments on 18 configurations and 3 metrics, \ours{} consistently achieves the highest accuracy with the best class discovery to OOD filtering balance compared to state-of-the-art competitor approaches.
@inproceedings{Schmidt2025a, author = {Schmidt, Sebastian and Schenk, Leonard and Schwinn, Leo and Günnemann, Stephan}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, title = {Joint Out-of-Distribution Filtering and Data Discovery Active Learning}, url = {http://arxiv.org/abs/2503.02491}, year = {2025}, }

Generalized Synchronized Active Learning for Multi-Agent-Based Data Selection on Mobile Robotic Systems

Sebastian Schmidt, Lukas Stappen, Leo Schwinn, and 1 more author

IEEE Robotics and Automation Letters, 2024

Abs DOI Bib PDF Website

@article{Schmidt2024b,
  author = {Schmidt, Sebastian and Stappen, Lukas and Schwinn, Leo and Günnemann, Stephan},
  journal = {IEEE Robotics and Automation Letters},
  title = {Generalized Synchronized Active Learning for Multi-Agent-Based Data Selection on Mobile Robotic Systems},
  year = {2024},
  volume = {9},
  number = {10},
  pages = {8659-8666},
  keywords = {Robots;Robot kinematics;Uncertainty;Data centers;Synchronization;Task analysis;Streams;Computer vision for transportation;deep learning for visual perception;deep learning methods},
  url = {https://ieeexplore.ieee.org/abstract/document/10637683},
  doi = {10.1109/LRA.2024.3444670},
}

GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation

Phillip Mueller, Talip Uenlue, Sebastian Schmidt, and 4 more authors

In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2025

Abs Bib PDF Website

@inproceedings{mueller2025,
  title = {GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation},
  author = {Mueller, Phillip and Uenlue, Talip and Schmidt, Sebastian and Kollovieh, Marcel and Fan, Jiajie and G\"unnemann, Stephan and Mikelsons, Lars},
  year = {2025},
  month = oct,
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  pages = {6374--6384},
  url = {TBD},
}