Mark obtained his M.Sc. in Computer Science (minor Medical Science) from the RWTH Aachen University in 2019. During his studies, Mark worked with Dr. Aljosa Osep and Prof. Bastian Leibe on panoptic segmentation and on open-set video object proposals. Before that, he spent one semester abroad at the University of California, Davis. In summer 2020, Mark did a research internship at Google where he continued working as a part-time student researcher until early 2021. In October 2020, Mark joined the Dynamic Vision and Learning group (DVL) and the Computer Vision Group (CVG) to pursue his Ph.D. under the supervision of Prof. Dr. Leal-Taixé and Prof. Daniel Cremers. His current research interests lie with (video) panoptic segmentation.

• Reviewer for CVPR (best reviewer award), ECCV, ICCV, TPAMI, CVIU, IROS, ICRA, RAL.
• Host/Organizer of the ICCV 2021 workshop Segmenting and Tracking Every Point and Pixel (Recordings).
• Co-Organizer of the CVPR 2022 workshop How far can synthetic data take us?.
• Co-Organizer of the CVPR 2023 workshop 2nd Workshop on Tracking and Its Many Guises.
• Admin of the MOTChallenge

• Please do not email me for a Bachelor thesis.
• Please do not email me for an external thesis.
• For a master thesis or guided research project, please attach your CV and transcript.
• I mostly recruit students that took our lectures prior to the project.
• My topics are usually related to segmentation tasks, but I'm always interested in your proposal!

• Seminar on Segmenting everything, everywhere, all at once in WS23.
• Computer Vision III: Detection, Segmentation and Tracking (CV3DST) in SS22.
• Computer Vision III: Detection, Segmentation and Tracking (CV3DST) in WS21.

Export as PDF, XML, TEX or BIB

2024
Preprints
[]		An Image is Worth 32 Tokens for Reconstruction and Generation (Q Yu, M Weber, X Deng, X Shen, D Cremers and LC Chen), In arXiv preprint arxiv:2406.07550, 2024. ([project page]) [bibtex]
Conference and Workshop Papers
[]		MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation (L Yang, L Hoyer, M Weber, T Fischer, D Dai, L Leal-Taixé, D Cremers, M Pollefeys and LV Gool), In European Conference on Computer Vision (ECCV), 2024.  [bibtex]
2022
Conference and Workshop Papers
[]		DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation (A Toker, L Kondmann, M Weber, M Eisenberger, C Andres, J Hu, A Hoderlein, C Senaras, T Davis, D Cremers, G Marchisio, X Zhu and L Leal-Taixe), In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.  [bibtex] [pdf]
2021
Preprints
[]		DeepLab2: A TensorFlow Library for Deep Labeling (M Weber, H Wang, S Qiao, J Xie, MD Collins, Y Zhu, L Yuan, D Kim, Q Yu, D Cremers and others), In arXiv preprint arXiv:2106.09748, 2021.  [bibtex]
Conference and Workshop Papers
[]		4D Panoptic LiDAR Segmentation (M Aygun, A Osep, M Weber, M Maximov, C Stachniss, J Behley and L Leal-Taixé), In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.  [bibtex]
[]		STEP: Segmenting and Tracking Every Pixel (M Weber, J Xie, M Collins, Y Zhu, P Voigtlaender, H Adam, B Green, A Geiger, B Leibe, D Cremers and others), In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Track on Datasets and Benchmarks), volume 1, 2021.  [bibtex]
2020
Conference and Workshop Papers
[]		4D generic video object proposals (A Ošep, P Voigtlaender, M Weber, J Luiten and B Leibe), In International Conference on Robotics and Automation (ICRA), 2020.  [bibtex]
[]		Single-Shot Panoptic Segmentation (M Weber, J Luiten and B Leibe), In International Conference on Intelligent Robots and Systems (IROS), 2020.  [bibtex]
2019
Conference and Workshop Papers
[]		Visual person understanding through multi-task and multi-dataset learning (K Pfeiffer, A Hermans, I Sárándi, M Weber and B Leibe), In German Conference on Pattern Recognition (GCPR), 2019.  [bibtex]