Technical University of Munich

Lukas Koestler

PhD student

School of Computation, Information and Technology
Informatics 9
Boltzmannstrasse 3
85748 Garching
Germany

Tel: +49-89-289-17763
Fax: +49-89-289-17757
Office: 02.09.038
Mail: Lukas.Koestler@tum.de

Please also see my personal webpage and my twitter account.

Student Projects

Due to an upcoming internship I am currently not looking for students. I will be back by the beginning of April 2023 and would be happy to discuss projects that start after that.

I am looking for motivated and talented students to work on topics in 3D Deep Learning, 3D reconstruction, and dense monocular SLAM. Please contact me directly by mail and highlight your relevant academic experience and programming skills. Additionally, please include a CV and a recent transcript.

Publications

Export as PDF, XML, TEX or BIB

Preprints

2022
[]		Masked Event Modeling: Self-Supervised Pretraining for Event Cameras (S Klenk, D Bonello, L Koestler and D Cremers), In arXiv preprint arXiv:2212.10368, 2022. [bibtex] [arXiv:2212.10368]
[]		E-NeRF: Neural Radiance Fields from a Moving Event Camera (S Klenk, L Koestler, D Scaramuzza and D Cremers), In arXiv preprint arXiv:2208.11300, 2022. [bibtex] [arXiv:2208.11300]

Conference and Workshop Papers
2023
[]		Neural Implicit Representations for Physical Parameter Inference from a Single Video (F Hofherr, L Koestler, F Bernard and D Cremers), In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023. ([project page]) [bibtex] [arXiv:2204.14030]
2022
[]		Intrinsic Neural Fields: Learning Functions on Manifolds (L Koestler, D Grittner, M Moeller, D Cremers and Z Lähner), In European Conference on Computer Vision (ECCV), 2022. (Code will be released soon.) [bibtex] [arXiv:2203.07967] [pdf]
[]		The Probabilistic Normal Epipolar Constraint for Frame-To-Frame Rotation Optimization under Uncertain Feature Positions (D Muhle, L Koestler, N Demmel, F Bernard and D Cremers), In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. ([project page]) [bibtex] [arXiv:2204.02256] [pdf]
2021
[]		TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo (L Koestler, N Yang, N Zeller and D Cremers), In Conference on Robot Learning (CoRL), 2021. ([GitHub][video][project page]) [bibtex] [arXiv:2111.07418] [pdf]3DV'21 Best Demo Award
2020
[]		Learning Monocular 3D Vehicle Detection without 3D Bounding Box Labels (L. Koestler, N. Yang, R. Wang and D. Cremers), In Proceedings of the German Conference on Pattern Recognition (GCPR), 2020. ([project page][video]) [bibtex] [pdf]