Daniel Cremers How Can We Get 3D-Pictures of Moving Objects with Just One Camera?

Daniel Cremers is Professor for Computer Science and Mathematics at the Technical University Munich. As a postdoctoral researcher, Cremers spent two years at the University of California, Los Angeles and one year as a Siemens Corporate researcher at Princeton, New Jersey. For his research in the field of computer vision and mathematical image analysis, Cremers was awarded the esteemed Leibniz Award 2016. Cremers seeks to tackle the difficulty of representing a 3-dimensional world on camera.

Area of Research

Computer Vision, Optimization, Image Analysis

Daniel Cremers, Mikael Rousson and Rachid Deriche. "A Review of Statistical Approaches to Level Set Segmentation: Integrating Color, Texture, Motion and Shape." International Journal of Computer Vision 72 (2007): 195-215.  
Daniel Cremers, Florian Tischhäuser, Joachim Weickert and Christoph Schnörr. "Diffusion Snakes: Introducing Statistical Shape Knowledge into the Mumford-Shah Functional." International Journal of Computer Vision 50 (2002): 295-313.  
Daniel Cremers. "Dynamical Statistical Shape Priors for Level Set Based Tracking." Pattern Analysis and Machine Intelligence, IEEE Transactions on 28 (2006): 1262-1273.  
Daniel Cremers and Stefano Soatto. "Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation." International Journal of Computer Vision 62 (2005): 249-265.  
Thomas Pock, Daniel Cremers, Horst Bischof and Antonin Chambolle. "Global Solutions of Variational Models with Convex Regularization." SIAM Journal on Imaging Sciences 3 (2010): 1122-1145.  

since 2009

Professor for Computer Science (since 2012 Dual Affiliation in Mathematics)

Technical University of Munich (Technische Universität München) (more details)

Department of Informatics

2007

Visiting Researcher (with Prof. A. Blake)

Microsoft Research, Cambridge, UK

2005-2009

Professor for Computer Science

University of Bonn (Rheinische Friedrich-Wilhelms-Universität Bonn)

Head of Computer Vision and Pattern Recognition Group

2004-2005

Research Scientist

Siemens Corporate Research, Princeton, NJ

2002-2004

Postdoctoral Researcher

University of California, Los Angeles

Department of Computer Science, with Prof. Stefano Soatto at the UCLA Vision Lab

1999-2002

Research Fellow

University of Mannheim (Universität Mannheim)

Department of Mathematics and Computer Science, with Prof. Christoph Schnörr in the Computer Vision Group

1998-1999

Research Fellow

Humboldt University of Berlin (Humboldt-Universität zu Berlin)

Department of Biology, with Prof. Andreas V. M. Herz at the Institute of Theoretical Biology

1996-1998

Teaching and Research Assistant

Heidelberg University (Ruprecht-Karls-Universität Heidelberg)

Department of Physics, with Prof. Andreas Mielke and Prof. Franz Wegner, Statistical Physics

2002

PhD in Computer Science

University of Mannheim (Universität Mannheim)

Thesis "Statistical Shape Knowledge in Variational Image Segmentation"

1997

Diploma in Theoretical Physics

Ruprecht-Karls-Universität Heidelberg

Prizes

Google Faculty Research Award (2014)

ISMAR Best Short Paper Award (2014)

ICRA Best Vision Paper Nomination (2013)

UAV-g Best Paper Award (2013)

Listed among Germany's Top 40 Researchers below 40 (2010)

ACCV Best Paper Honorable Mention (Töppe, Oswald, Rother and Cremers) (2010)

GFFT Preis for PhD thesis of Andreas Wedel (2010)

DAGM Main Conference Award (Goldlücke and Cremers) (2009)

DAGM Paper Award (Oswald, Töppe, Kolev and Cremers) (2009)

UCLA Chancellor's Award for Postdoctoral Research (2005)

Olympus Award (2004)

Best Paper of the Year 2003, Intl. Pattern Recognition Society (2004)

Nomination for Best Thesis in Computer Science 2002 by the German Society of Computer Science (2003)

DAGM Main Conference Award (2001)

Fellowships

Cluster of Excellency Hausdorff Center for Mathematics (2007)

Emmy Noether Scholarship, DFG (2005)

Fulbright Scholar in Indiana (Indiana State Univ.) and New York (SUNY at Stony Brooks) (1994-1995) )

Member of Studienstiftung des deutschen Volkes (1993-1998)

ERC Starting Grant (2009)

© TUM Fotostelle

Technical University of Munich (Technische Universität München)

München, Germany

"Technische Universität München (TUM) is one of Europe’s top universities. It is committed to excellence in research and teaching, interdisciplinaryeducation and the active promotion of promising young scientists. The university also forges strong links with companies and scientific institutionsacross the world. TUM was one of the first universities in Germany to be named a University of Excellence. Moreover, TUM regularly ranks among the best European universities in international rankings." (Source)

Map

The recovering of our 3D-world with only one camera is a challenge in many fields ranging from self-driving cars to plastic surgery. In this video DANIEL CREMERS presents innovations from computer vision to tackle that challenge. Modelling the movement of a camera in addition to the geometry of the depicted world and using new algorithms allow the recovery of more pictures in real-time. The algorithms compute the highest possible consistency between consecutive images and make it possible to recover even moving objects with the limited computational space of a laptop.

LT Video Publication DOI: http://dx.doi.org/10.21036/LTPUB10144

LSD-SLAM: Large-Scale Direct Monocular SLAM

  • Jakob Engel, Thomas Schöps and Daniel Cremers
  • Computer Vision–ECCV 2014
  • Published in 2014

Chicago

Jakob Engel, Thomas Schöps and Daniel Cremers. "LSD-SLAM: Large-Scale Direct Monocular SLAM." In Computer Vision–ECCV 2014 Springer, 2014: 834–849.

LSD-SLAM: Large-Scale Direct Monocular SLAM

  • Jakob Engel; Thomas Schöps; Daniel Cremers
  • European Conference on Computer Vision (Working Paper)
  • Published in 2014

Chicago

Jakob Engel, Thomas Schöps and Daniel Cremers. "LSD-SLAM: Large-Scale Direct Monocular SLAM." In European Conference on Computer Vision (Working Paper) 2014.