Mathematical Image Analysis Group, Saarland University

Welcome to the homepage of

Oliver Demetz

Former Research Assistant

Position: Former Research Assistant

Phone:

Fax:

E-mail: demetz - at - mia.uni-saarland.de

(please replace anti-spam -at- by @)

Address:

Research Interests

Publications

Journal Articles

D. Hafner, O. Demetz, J. Weickert, M. Reißel:
Mathematical foundations and generalisations of the census transform for robust optic flow computation.
To appear in Journal of Mathematical Imaging and Vision.
Revised version of Technical Report No. 337, Department of Mathematics, Saarland University, Saarbrücken, Germany, October 2013.
O. Demetz, D. Hafner, J. Weickert:
Morphologically invariant matching of structures with the complete rank transform.
International Journal of Computer Vision, Online First.
Revised version of Technical Report No. 348, Department of Mathematics, Saarland University, Saarbrücken, Germany, May 2014.

Conference Publications

O. Demetz, J. Weickert, A. Bruhn, M. Welk:
Beauty with variational methods: An optic flow approach to hairstyle simulation.
In F. Sgallari, A. Murli, N. Paragios (Eds.), Scale Space and Variational Methods in Computer Vision. Lecture Notes in Computer Science, Vol. 4485, 825-836, Springer, Berlin, 2007.
O. Demetz, J. Weickert, A. Bruhn, and H. Zimmer:
Optic Flow Scale Space.
In A.M. Bruckstein et al. (Eds.), Scale Space and Variational Methods in Computer Vision. Lecture Notes in Computer Science, Vol. 6667, 713-724, Springer, Berlin, 2011.
C. Schroers, H. Zimmer, L. Valgaerts, A. Bruhn, O. Demetz, J. Weickert:
Anisotropic range image integration.
In A. Pinz, T. Pock, H. Bischof, F. Leberl (Eds.), Pattern Recognition. Lecture Notes in Computer Science, Vol. 7476, 73-82, Springer, Berlin, 2012.
Awarded a DAGM-OAGM 2012 Paper Prize.
V. Kramarev, O.Demetz, C. Schroers, J. Weickert:
Cross Anisotropic Cost Volume Filtering for Segmentation.
In K. M. Lee, Y. Matsushita, J. M. Rehg, Z. Hu (Eds.): Computer Vision - ACCV 2012. Lecture Notes in Computer Science Vol. 7724, 803-814. Springer, Berlin, 2013.
D. Hafner, O. Demetz, J. Weickert:
Why is the census transform good for robust optic flow computation?
In A. Kuijper, K. Bredies, T. Pock, H. Bischof (Eds.): Scale-Space and Variational Methods in Computer Vision. Lecture Notes in Computer Science, Vol. 7893, 210-221, Springer, Berlin, 2013.
O. Demetz, D. Hafner, J. Weickert:
The complete rank transform: A tool for accurate and morphologically invariant matching of structures.
In T. Burghardt, D. Damen, W. Mayol-Cuevas and M. Mirmehdi: Proc. 24th British Machine Vision Conference, BMVA Press, 2013.
Awarded the Maria Petrou Prize for Invariance in Computer Vision.
D. Hafner, O. Demetz, J. Weickert:
Simultaneous HDR and optic flow computation.
In Proc. 22nd International Conference on Pattern Recognition (ICPR 2014, Stockholm, Sweden, August 2014), IEEE Computer Society Press, August 2014.
O. Demetz, M. Stoll, S. Volz, J. Weickert, A. Bruhn:
Learning brightness transfer functions for the joint recovery of illumination changes and optical flow.
In D. Fleet, T. Pajdla, B. Schiele, T. Tuytelaars (Eds.): Computer Vision - ECCV 2014, Part I, LNCS 8689, pp. 455--471. Springer International Publishing Switzerland (2014)

Technical Reports

O. Demetz, D. Hafner, J. Weickert:
Morphologically Invariant Matching of Structures with the Complete Rank Transform.
Technical Report No. 348, Department of Mathematics, Saarland University, Saarbrücken, Germany, May 2014.

Theses