Research Profile · Publications · Teaching

Nils Morbitzer

Doctoral Candidate @ TUM CAMP Computer Vision Lab

I work on dynamic 3D reconstruction, 3D scene understanding, and world models. This site collects my publications, preprints, teaching, and selected academic work.

GitHub Scholar LinkedIn TUM Webpage
Portrait of Nils Morbitzer Profile Photo
Munich nils.morbitzer@tum.de
Computer Vision Machine Learning Autonomous Driving

01 · About

Curious about dynamic 3D worlds.

Hey, I am Nils, a 2nd-year PhD student at the CAMP Computer Vision Lab of the Technical University of Munich (TUM) supervised by Federico Tombari and Stefano Gasperini. My current work focuses on dynamic 3D reconstruction and world models. I completed my M.Sc. in Computer Science also at TUM, where I focused on Computer Vision, Machine Learning, and Autonomous Driving.

In my free time, I love playing beach volleyball in the summer and indoor volleyball when the seasons change. I also enjoy going road cycling and dancing Boogie Woogie.

PhD Doctoral candidate at TUM
3D Dynamic reconstruction and world models
Sport Volleyball, road cycling, and dancing

02 · News

Recent updates

  1. Attended the KTH RPL Summer School in Stockholm, Sweden.
  2. Our preprint on Prompting Diffusion Models for Zero-Shot Instance Segmentation is on arXiv.
  3. Our preprint on Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-Motion is on arXiv.
  4. Our paper on Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-Motion got accepted at ICML 2026.
  5. Attended ICVSS 2025 on Computer Vision for Spatial and Physical Intelligence in Sicily, Italy.
  6. Attended ECCV 2024 in Milan, Italy.
  7. Started my PhD on dynamic 3D reconstruction & scene understanding at TUM CAMP chair supervised by Federico Tombari and Stefano Gasperini.
  8. Successfully completed my master's in computer science.
  9. Presented our paper on Robust Monocular Depth Estimation under Challenging Conditions at ICCV 2023 in Paris, France.
  10. Our paper on Robust Monocular Depth Estimation under Challenging Conditions got accepted at ICCV 2023.

03 · Publications & Preprints

Accepted papers and current preprints

2026
FR3D paper teaser
AcceptedICML 2026

FR3D · Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-Motion

Nils Morbitzer*, Jonathan Evers*, Artem Savkin, Thomas Stauner, Nassir Navab, Federico Tombari, Stefano Gasperini

ICML, 2026.

arXiv ICML Project 
@inproceedings{morbitzer_evers2026fr3d,
title={Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-Motion},
author={Morbitzer, Nils and Evers, Jonathan and Savkin, Artem and Stauner, Thomas and Navab, Nassir and Tombari, Federico and Gasperini, Stefano},
booktitle={Proceedings of the 43rd International Conference on Machine Learning},
series={Proceedings of Machine Learning Research},
publisher={PMLR},
year={2026},
}
2026
Prompt2Seg paper teaser
PreprintarXiv

Prompt2Seg · Prompting Diffusion Models for Zero-Shot Instance Segmentation

Irem Zeynep Alagöz*, Nils Morbitzer*, Andrea Ramazzina, Nassir Navab, Federico Tombari

arXiv preprint, 2026.

arXiv Project 
@article{alagoz2026prompting,
  title={Prompting Diffusion Models for Zero-Shot Instance Segmentation},
  author={Alag{\"o}z, Irem Zeynep and Morbitzer, Nils and Ramazzina, Andrea and Navab, Nassir and Tombari, Federico and Gasperini, Stefano},
  journal={arXiv preprint arXiv:2606.22660},
  year={2026}
}
2023
md4all paper teaser
AcceptedICCV 2023

md4all: Robust Monocular Depth Estimation under Challenging Conditions

Stefano Gasperini*, Nils Morbitzer*, HyunJun Jung, Nassir Navab, Federico Tombari

ICCV, 2023.

arXiv ICCV Code Project 
@inproceedings{gasperini_morbitzer2023md4all,
  title={md4all · Robust Monocular Depth Estimation under Challenging Conditions},
  author={Gasperini, Stefano and Morbitzer, Nils and Jung, HyunJun and Navab, Nassir and Tombari, Federico},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year={2023},
  pages={8177-8186}
}

04 · Experience

Education and academic roles

Doctoral Candidate

ResearchDynamic 3D ReconstructionWorld Models

TUM CAMP Computer Vision Lab · Supervised by Federico Tombari and Stefano Gasperini.

M.Sc. Informatics

Grade: 1.3 (distinction)Computer VisionMachine LearningAutonomous Driving

Technical University of Munich · Thesis on Camera Parameter Optimization for NeRFs from Sparse Inputs and Noisy Poses.

B.Sc. Computer Science

Grade: 1.5Computer Science TheoryInternship Semester

Julius Maximilian University of Würzburg · Further studies in core computer science concepts and theory, including one internship semester.

B.Sc. Aerospace Computer Science

Grade: 1.2 (distinction)AerospaceComputer ScienceSatellites

Julius Maximilian University of Würzburg · Aerospace-focused computer science major · Thesis on Inter-satellite Communication for CubeSat Formation Flight Mission NetSat.

05 · Service

Reviewing, teaching, and academic development

Ongoing

Reviewing Service

Reviewer for NeurIPS, 3DV, and ICRA.

Ongoing

Teaching and Supervision

Supervised several master's thesis students, as well as student projects in the chair's practical course and seminar.

2025 - 2026

Research Schools

Participation in international computer vision and robotics summer schools, including KTH RPL and ICVSS.

06 · Contact

Interested in a collaboration?

Reach out about research ideas, thesis projects, academic collaborations, or shared tools.

GitHub