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

Technical University of Munich

Menu
Home Research Areas Optical Flow Estimation

This is an old revision of the document!


Optical Flow Estimation

Estimating the motion of every pixel in a sequence of images is a problem with many applications in computer vision, such as image segmentation, object classification,visual odometry, and driver assistance.

In general, optical flow describes a sparse or dense vector field, where a displacement vector is assigned to certain pixel position, that points to where that pixel can be found in another image. In the context of scene flow estimation, which is performed on images with additional depth values, every pixel is assigned a depth displacement as well.

Since much of the structural information of a 3D scene gets lost in the imaging process, so does the motion information. The estimation of the "correct" projected motion in an image sequence is therefore highly ill-posed and has to be aided by additional priors such as the regularity of the motion. Our group mainly focuses on optical flow estimation by means of variational methods, that allow a clear formulation of the assumptions incorporated into the estimation process and generally produce dense vector fields.

Contact: Frank Steinbrücker

Related publications


Export as PDF, TEX or BIB

Sort Order:  by type by year
Book Chapters Journal Articles Preprints Conference and Workshop Papers PhD Thesis 
Book Chapters
2006
[]A survey on variational optic flow methods for small displacements (J. Weickert, A. Bruhn, T. Brox and N. Papenberg), Chapter in Mathematical Models for Registration and Applications to Medical Imaging (O. Scherzer, ed.), Springer, volume 10, 2006.  [bibtex]
[]Adaptive structure tensors and their applications (T. Brox, R. van den Boomgaard, F. B. Lauze, J. van de Weijer, J. Weickert, P. Mrázek and P. Kornprobst), Chapter in Visualization and Processing of Tensor Fields (J. Weickert, H. Hagen, eds.), Springer, 2006.  [bibtex]
Book Chapters Journal Articles Preprints Conference and Workshop Papers PhD Thesis 
Journal Articles
2014
[]Convex Relaxation of Vectorial Problems with Coupled Regularization (E. Strekalovskiy, A. Chambolle and D. Cremers), In SIAM Journal on Imaging Sciences, volume 7, 2014.  [bibtex] [pdf]
2012
[]The Natural Total Variation Which Arises from Geometric Measure Theory (B. Goldluecke, E. Strekalovskiy and D. Cremers), In SIAM Journal on Imaging Sciences, volume 5, 2012.  [bibtex] [pdf]
2011
[]Bootstrap Optical Flow and Uncertainty Measure (J. Kybic and C. Nieuwenhuis), In Computer Vision and Image Understanding, volume 115, 2011.  [bibtex] [pdf]
[]Motion Field Estimation from Alternate Exposure Images (A. Sellent, M. Eisemann, B. Goldluecke, D. Cremers and M. Magnor), In IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 33, 2011.  [bibtex] [pdf]
[]Stereoscopic Scene Flow Computation for 3D Motion Understanding (A. Wedel, T. Brox, T. Vaudrey, C. Rabe, U. Franke and D. Cremers), In International Journal of Computer Vision, volume 95, 2011.  [bibtex] [pdf]
2005
[]Motion Competition: A variational framework for piecewise parametric motion segmentation (D. Cremers and S. Soatto), In International Journal of Computer Vision, volume 62, 2005.  [bibtex] [pdf]
2003
[]Statistical shape knowledge in variational motion segmentation (D. Cremers and C. Schnörr), In Image and Vision Computing, volume 21, 2003.  [bibtex] [pdf]
Book Chapters Journal Articles Preprints Conference and Workshop Papers PhD Thesis 
Preprints
2006
[]Highly accurate optic flow computation with theoretically justified warping (N. Papenberg, A. Bruhn, T. Brox, S. Didas and J. Weickert), In International Journal of Computer Vision, volume 67, 2006.  [bibtex]
Book Chapters Journal Articles Preprints Conference and Workshop Papers PhD Thesis 
Conference and Workshop Papers
2018
[]What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation? (Nikolaus Mayer, Eddy Ilg, Philipp Fischer, Caner Hazirbas, Daniel Cremers, Alexey Dosovitskiy and Thomas Brox), In International Journal of Computer Vision, 2018. (arxiv) [bibtex] [arXiv:1801.06397]
2016
[]A Convex Solution to Spatially-Regularized Correspondence Problems (T. Windheuser and D. Cremers), In European Conference on Computer Vision (ECCV), 2016.  [bibtex] [pdf]
[] A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation (N.Mayer, E.Ilg, P.Haeusser, P.Fischer, D.Cremers, A.Dosovitskiy and T.Brox), In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (arXiv:1512.02134) [bibtex] [pdf] [pdf]
2015
[]FlowNet: Learning Optical Flow with Convolutional Networks (A. Dosovitskiy, P. Fischer, E. Ilg, P. Haeusser, C. Hazirbas, V. Golkov, P. van der Smagt, D. Cremers and T. Brox), In IEEE International Conference on Computer Vision (ICCV), 2015. ([video],[code]) [bibtex] [doi] [pdf]
2011
[]Multi-object tracking via high accuracy optical flow and finite set statistics (M. Schikora, W. Koch and D. Cremers), In International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011.  [bibtex] [pdf]
[]Tight Convex Relaxations for Vector-Valued Labeling Problems (E. Strekalovskiy, B. Goldluecke and D. Cremers), In IEEE International Conference on Computer Vision (ICCV), 2011.  [bibtex] [pdf]
2010
[]Interactive Motion Segmentation (C. Nieuwenhuis, B. Berkels and M. Rumpf), In Pattern Recognition (Proc. DAGM), Springer, volume 6376, 2010.  [bibtex] [pdf]
[]Complex Motion Models for Simple Optical Flow Estimation (C. Nieuwenhuis and D. Kondermann), In Pattern Recognition (Proc. DAGM), Springer, volume 6376, 2010.  [bibtex] [pdf]
2009
[]Advanced Data Terms for Variational Optic Flow Estimation (F. Steinbruecker, T. Pock and D. Cremers), In Proceedings Vision, Modeling and Visualization (VMV), 2009.  [bibtex] [pdf]
[]Reconstructing Optical Flow Fields by Motion Inpainting (B. Berkels, C. Nieuwenhuis, C. Garbe and M. Rumpf), In Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), Springer, volume 5681, 2009.  [bibtex] [pdf]
[]Video Super Resolution using Duality Based TV-L1 Optical Flow (D. Mitzel, T. Pock, T. Schoenemann and D. Cremers), In Pattern Recognition (Proc. DAGM), 2009.  [bibtex] [pdf]
[]Large Displacement Optical Flow Computation without Warping (F. Steinbruecker, T. Pock and D. Cremers), In IEEE International Conference on Computer Vision (ICCV), 2009.  [bibtex] [pdf]
[]Structure- and Motion-adaptive Regularization for High Accuracy Optic Flow (A. Wedel, D. Cremers, T. Pock and H. Bischof), In IEEE International Conference on Computer Vision (ICCV), 2009.  [bibtex] [pdf]
[]Variational Optical Flow from Alternate Exposure Images (A. Sellent, M. Eisemann, B. Goldluecke, T. Pock, D. Cremers and M. Magnor), In Proceedings Vision, Modeling and Visualization (VMV), 2009.  [bibtex] [pdf]
2008
[]An Improved Algorithm for TV-L1 Optical Flow (A. Wedel, T. Pock, C. Zach, D. Cremers and H. Bischof), In Proc. of the Dagstuhl Motion Workshop, Springer, 2008.  [bibtex] [pdf]
[]Duality TV-L1 Flow with Fundamental Matrix Prior (A. Wedel, T. Pock, J. Braun, U. Franke and D. Cremers), In Image Vision and Computing, 2008.  [bibtex] [pdf]
[]Efficient Dense Scene Flow from Sparse or Dense Stereo Data (A. Wedel, C. Rabe, T. Vaudrey, T. Brox, U. Franke and D. Cremers), In European Conference on Computer Vision (ECCV), 2008.  [bibtex] [pdf]
2007
[]A Duality Based Algorithm for TV-L1-Optical-Flow Image Registration (T. Pock, M. Urschler, C. Zach, R. Beichel and H. Bischof), In 10th International Conference on Medical Image Computing and Computer Assisted Intervention, 2007.  [bibtex]
[]A Duality Based Approach for Realtime TV-L1 Optical Flow (C. Zach, T. Pock and H. Bischof), In Pattern Recognition (Proc. DAGM), 2007.  [bibtex]
2006
[]Variational motion segmentation with level sets (T. Brox, A. Bruhn and J. Weickert), In European Conference on Computer Vision (ECCV) (A. Leonardis, H. Bischof, A. Pinz, eds.), Springer, volume 3951, 2006.  [bibtex] [pdf]
2004
[]High accuracy optical flow estimation based on a theory for warping (T. Brox, A. Bruhn, N. Papenberg and J. Weickert), In European Conference on Computer Vision (ECCV) (T. Pajdla, J. Matas, eds.), Springer, volume 3024, 2004.  [bibtex] [pdf]Received "The Longuet-Higgins Best Paper Award"
2003
[]A generative model based approach to motion segmentation (D. Cremers and A. L. Yuille), In Pattern Recognition (Proc. DAGM) (B. Michaelis, G. Krell, eds.), Springer, volume 2781, 2003.  [bibtex] [pdf]
[]Variational space-time motion segmentation (D. Cremers and S. Soatto), In IEEE International Conference on Computer Vision (ICCV) (B. Triggs, A. Zisserman, eds.), volume 2, 2003.  [bibtex] [pdf]
2002
[]Statistical shape knowledge in variational motion segmentation (D. Cremers and C. Schnörr), In 1st Internat. Workshop on Generative-Model-Based Vision (A. Pece, Y. N. Wu, R. Larsen, eds.), Univ. of Copenhagen, 2002. (http://www.diku.dk/research/published/2002/02-01) [bibtex]
[]Nonlinear matrix diffusion for optic flow estimation (T. Brox and J. Weickert), In Pattern Recognition (Proc. DAGM) (L. van Gool, ed.), Springer, volume 2449, 2002.  [bibtex] [pdf]
Book Chapters Journal Articles Preprints Conference and Workshop Papers PhD Thesis 
PhD Thesis
2009
[]Restoration and Prostprocessing of Optical Flows (C. Nieuwenhuis), PhD thesis, Faculty of Mathematics and Computer Science, Heidelberg University, 2009.  [bibtex] [pdf]
Powered by bibtexbrowser
Export as PDF, TEX or BIB

Rechte Seite

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching

info@vision.in.tum.de