Direkt zum Inhalt springen
Computer Vision Group
TUM Department of Informatics
Technical University of Munich

Technical University of Munich

Menu

Links

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching info@vision.in.tum.de

Follow us on:
CVG Group DVL Group

News

02.10.2020

We have five papers accepted to 3DV 2020!

30.09.2020

Our effcient deep network architectures form the AI engine of the project Slow Down COVID-19 at Harvard.

24.07.2020

Our practical course "Vision-based Navigation" (WS18, SS19) by Dr. Vladyslav Usenko and Nikolaus Demmel was honored as best practical course in the academic year 2018/2019 by the department for Informatics.

07.05.2020

We are organizing a workshop on Map-based Localization for Autonomous Driving at ECCV 2020, Glasgow, UK.

13.04.2020

Daniel Cremers received an ERC Advanced Grant (3.5 Mio Euro) for pioneering frontier research from the European Research Council. This constitutes his fifth ERC grant.

More


Björn Häfner

PhD StudentTechnical University of Munich

Department of Informatics
Informatics 9
Boltzmannstrasse 3
85748 Garching
Germany

Tel: +49-89-289-17784
Fax: +49-89-289-17757
Office: 02.09.053
Mail: bjoern.haefner@tum.de

Research Interests

I am interested in RGB-D data processing for 3D reconstruction using variational methods, especially photometric approaches and super-resolution.

Brief Bio

I received my B.Sc. in Mathematics from the OTH Regensburg in 2013 and my M.Sc. in Mathematics in Science and Engineering from the Technical University of Munich in 2016. Since mid November 2016, I am a PhD student in the Computer Vision Group, headed by Prof. Dr. Daniel Cremers at TUM. In May 2019 I was a visiting Ph.D. student at the GREYC Image Group, Caen, France under supervision of Yvain Quéau. From September 2019 until February 2020 I was interning as Research Intern at Facebook Reality Labs in Cork, Ireland under supervision of Thomas Whelan. From July 2020 onwards I'll be working part-time at Pro Unlimited @ Facebook as an External Research Collaborator to continue the project of my internship at Facebook Reality Labs.

Publications


Export as PDF, XML, TEX or BIB

Book Chapters
2020
[] On the Well-Posedness of Uncalibrated Photometric Stereo Under General Lighting (M Brahimi, Y Quéau, B Haefner and D Cremers), Chapter in Advances in Photometric 3D-Reconstruction (JD Durou, M Falcone, Y Quéau, S Tozza, eds.), Springer International Publishing, 2020.  [bibtex] [pdf] [doi] [pdf]
Journal Articles
2020
[]Photometric Depth Super-Resolution (B. Haefner, S. Peng, A. Verma, Y. Quéau and D. Cremers), In IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 42, 2020. ([supp] [project page] [ieeexplore]) [bibtex] [arXiv:1809.10097] [pdf]
Conference and Workshop Papers
2020
[]Inferring Super-Resolution Depth from a Moving Light-Source Enhanced RGB-D Sensor: A Variational Approach (L. Sang, B. Haefner and D. Cremers), In IEEE Winter Conference on Applications of Computer Vision (WACV), 2020. ([poster] [presentation] [code]) [bibtex] [arXiv:1912.06501] [pdf]Spotlight Presentation
2019
[]Variational Uncalibrated Photometric Stereo under General Lighting (B. Haefner, Z. Ye, M. Gao, T. Wu, Y. Quéau and D. Cremers), In International Conference on Computer Vision (ICCV), 2019. ([supp] [poster] [code] [cvf] [ieeexplore]) [bibtex] [arXiv:1904.03942] [pdf]
[]Photometric Segmentation: Simultaneous Photometric Stereo and Masking (B. Haefner, Y. Quéau and D. Cremers), In International Conference on 3D Vision (3DV), 2019. ([poster]) [bibtex] [pdf]Spotlight Presentation
2018
[]Fight ill-posedness with ill-posedness: Single-shot variational depth super-resolution from shading (B. Haefner, Y. Quéau, T. Möllenhoff and D. Cremers), In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. ([supp] [poster] [code] [cvf] [video]) [bibtex] [pdf] [video]Spotlight Presentation
2017
[]Depth Super-Resolution Meets Uncalibrated Photometric Stereo (S. Peng, B. Haefner, Y. Quéau and D. Cremers), In International Conference on Computer Vision Workshops (ICCVW), 2017. ([code] [cvf]) [bibtex] [arXiv:1708.00411] [pdf]Oral Presentation at ICCV Workshop on Color and Photometry in Computer Vision
Powered by bibtexbrowser
Export as PDF, XML, TEX or BIB

Talks

Reviewing Committee

Conferences Journals/Books
ECCV 2020 Springer
ICCV 2019
CVPR 2019

Student Supervision

Successfully defended works:

Name Project Topic Co-Supervisor
Florian Windolf Master's Thesis "High Quality Depth Maps from RGB-D Keyframes using Shape-from-Shading" Robert Maier
Lu Sang Master's Thesis "A Variational Approach to Depth Super-Resolution using Multi-View Photometric Stereo" Resulting Paper
Christoph Kick Master's Thesis "Cook-Torrance BRDF and Surface Geometry recovery under Near-Light Illumination"
Mohammed Brahimi Master's Thesis "Theoretical Analysis of the GBR and Lorentz Ambiguity of Uncalibrated Photometric Stereo" Resulting Paper Yvain Quéau
Christoph Kick Interdisciplinary Project in Mathematics "Reflectance and geometry estimation using nonlinear optimization of the Cook-Torrance model" Yvain Quéau
Alok Verma Project Management and Software Development for Medical Applications "Depth Super-Resolution using Shape-from-Shading and Reflectance Learning" Resulting Paper (Section 4) Yvain Quéau

Teaching

Winter 2020/21 - Seminar (organizer and supervisor)
Seminar: Recent Advances in 3D Computer Vision (2h / 5 ECTS)
together with Zorah Lähner and Mohammed Brahimi

Summer 2020 - Seminar (organizer and supervisor)
Seminar: The Evolution of Motion Estimation and Real-time 3D Reconstruction (2h / 5 ECTS)
together with Christiane Sommer and David Schubert

Summer 2019 - Seminar (organizer and supervisor)
Seminar: Recent Advances in 3D Computer Vision (2h / 5 ECTS)
together with Christiane Sommer

Winter 2018/19 - Seminar (organizer and supervisor)
Seminar: Recent Advances in 3D Computer Vision (2h / 5 ECTS)
together with Christiane Sommer

Summer 2018 - Practical Course (organizer, lecturer and tutor)
GPU Programming in Computer Vision (6h / 10 ECTS)
together with Robert Maier and David Schubert

Winter 2017/18 - Discrete Structures (tutor)
Diskrete Strukturen

Summer 2017 - Practical Course (organizer, lecturer and tutor)
GPU Programming in Computer Vision (6h / 10 ECTS)
together with Thomas Möllenhoff and Benedikt Löwenhauser

Connect

Rechte Seite

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching info@vision.in.tum.de

Follow us on:
CVG Group DVL Group

News

02.10.2020

We have five papers accepted to 3DV 2020!

30.09.2020

Our effcient deep network architectures form the AI engine of the project Slow Down COVID-19 at Harvard.

24.07.2020

Our practical course "Vision-based Navigation" (WS18, SS19) by Dr. Vladyslav Usenko and Nikolaus Demmel was honored as best practical course in the academic year 2018/2019 by the department for Informatics.

07.05.2020

We are organizing a workshop on Map-based Localization for Autonomous Driving at ECCV 2020, Glasgow, UK.

13.04.2020

Daniel Cremers received an ERC Advanced Grant (3.5 Mio Euro) for pioneering frontier research from the European Research Council. This constitutes his fifth ERC grant.

More