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

Technical University of Munich

Home Members Björn Häfner

Björn Häfner

PhD StudentTechnische Universität München

Department of Computer Science
Informatik 9
Boltzmannstrasse 3
85748 Garching

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

Research Interests

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

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.


Journal Articles
Photometric Depth Super-Resolution (B. Haefner, S. Peng, A. Verma, Y. Quéau, D. Cremers), In Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) Special Issue on RGB-D Vision: Methods and Applications, 2018.([supp] [arxiv]) [bib] [pdf]
Conference and Workshop Papers
Fight ill-posedness with ill-posedness: Single-shot variational depth super-resolution from shading (B. Haefner, Y. Quéau, T. Möllenhoff, D. Cremers), In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.([supp] [code] [cvf][video]) [bib] [pdf] [video]Spotlight Presentation
Depth Super-Resolution Meets Uncalibrated Photometric Stereo (S. Peng, B. Haefner, Y. Quéau, D. Cremers), In International Conference on Computer Vision Workshops (ICCVW), 2017.([code],[cvf]) [bib] [pdf]Oral Presentation at ICCV Workshop on Color and Photometry in Computer Vision
Powered by bibtexbrowser
Export as PDF or BIB


Salt Lake City, Utah @ CVPR spotlight presentation of our paper “Fight ill-posedness with ill-posedness: Single-shot variational depth super-resolution from shading”, Jun 18-22 2018
Bologna, Italy @ SIAM Minisymposium on Recent Trends in Photometric 3D-reconstruction, Jun 7 2018


I will be an official reviewer for CVPR 2019

Student Supervision

Successfully defended works:

Name Project Topic
Mohammed Brahimi Master's Thesis “Theoretical Analysis of the GBR and Lorentz Ambiguity of Uncalibrated Photometric Stereo”
Christoph Kick Interdisciplinary Project in Mathematics “Reflectance and geometry estimation using nonlinear optimization of the Cook-Torrance model”
Alok Verma Project Management and Software Development for Medical Applications “Depth Super-Resolution using Shape-from-Shading and Reflectance Learning” Resulting Paper (Section 4)


Summer 2018 - Practical Course (organizer and supervisor)
Seminar: Recent Advances in 3D Computer Vision (2h / 5 ECTS)

Summer 2018 - Practical Course (organizer, lecturer and tutor)
GPU Programming in Computer Vision (6h / 10 ECTS)

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

Summer 2017 - Practical Course (organizer, lecturer and tutor)
GPU Programming in Computer Vision (6h / 10 ECTS)


Rechte Seite

Informatik IX
Chair for Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching